{
  "aboutHtml": "<h4>Arbejdsmodel til lange processer</h4><p>Nemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.</p><h4>Arkitektur og kontekst</h4><p>Den hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.</p><p>Lag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.</p><h4>Fem forberedelsestrin</h4><ol><li>Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.</li><li>Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.</li><li>Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.</li><li>Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.</li><li>Efterfølgende numerisk komprimering af den offentliggjorte variant.</li></ol><p>Det sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.</p><h4>Sprog og versioner</h4><p>Engelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.</p><p>Egenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.</p>",
  "aboutText": "### Arbejdsmodel til lange processer\n\nNemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.\n\n### Arkitektur og kontekst\n\nDen hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.\n\nLag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.\n\n### Fem forberedelsestrin\n\n1. Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.\n2. Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.\n3. Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.\n4. Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.\n5. Efterfølgende numerisk komprimering af den offentliggjorte variant.\n\nDet sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.\n\n### Sprog og versioner\n\nEngelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.\n\nEgenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.",
  "editorialOverlay": {
    "copy_fields": {
      "practical_html": "<h3>Praktisk opgave</h3><p>Teknisk eksempel på engelsk</p><pre><code>Apply a document-grounded procedure\n\nUse these procedure excerpts to draft the next action for case C-09. [Rule 1] Packages with a damaged seal go to inspection. [Rule 2] Only inspection-cleared packages enter stock. [Record] C-09 has a damaged seal and no inspection result. Return the current permitted step, blocked step and supporting rule labels.</code></pre><h4>Forventet resultat</h4><pre><code>Three concise fields covering the permitted inspection step, blocked stocking and source evidence.</code></pre><h4>Kontrollér resultatet</h4><pre><code>Check that missing inspection clearance prevents stocking and does not become an assumed failed inspection.</code></pre>"
    },
    "copy_sha256": "5362e717ef1661ab97a515f9efc245661c5c5b0683b2609437ada7c4f375cb5a",
    "copy_source": {
      "locale": "da",
      "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7",
      "record_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
      "source_facts_sha256": "4a3834d94a10790f025d3ef6352bb99a9c4352b0163cd2ae1a1a430e088eedc0",
      "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6"
    },
    "html_sha256": "77a522bae0c8f4456b5c39349d77251bc9d93de56359fb41bfc3f77a2f2f4db7",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "da",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">NV</span><h2 id=\"sheet-title\">Nemotron 3.5 Lightning 30B A3B</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Luk\">×</button></div><div class=\"idline\"><span>NVIDIA /</span><code>nvidia/nemotron-3.5-lightning-30b-a3b</code><button type=\"button\" id=\"copy-id\">Kopiér ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Modelkortets afsnit\"><button type=\"button\" data-card-jump=\"overview\">Start</button><button type=\"button\" data-card-jump=\"methods\">Input og metoder</button><button type=\"button\" data-card-jump=\"pricing\">Priser</button><button type=\"button\" data-card-jump=\"examples\">Eksempler</button><button type=\"button\" data-card-jump=\"results\">Resultater</button><button type=\"button\" data-card-jump=\"aliases\">Aliaser</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API-metoder\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">Messages</button></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Start</h3><p class=\"mdesc-full\">Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog.</p><dl class=\"card-io\" data-card-io><div><dt>Accepterede input</dt><dd>Tekst</dd></div><div><dt>Resultater</dt><dd>Tekst</dd></div></dl><details class=\"card-about\"><summary>Om modellen</summary><p class=\"note-s\" data-model-method-boundary>Denne beskrivelse dækker modellens funktioner. Tilgængelige input, output og indstillinger i Ailoot står nedenfor for den valgte metode.</p><div class=\"mabout\" id=\"m-about\"><h4>Arbejdsmodel til lange processer</h4><p>Nemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.</p><h4>Arkitektur og kontekst</h4><p>Den hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.</p><p>Lag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.</p><h4>Fem forberedelsestrin</h4><ol><li>Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.</li><li>Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.</li><li>Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.</li><li>Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.</li><li>Efterfølgende numerisk komprimering af den offentliggjorte variant.</li></ol><p>Det sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.</p><h4>Sprog og versioner</h4><p>Engelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.</p><p>Egenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tilgængelig i Ailoot · input og metoder</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>Inputtyper</dt><dd><code>text</code></dd></div><div><dt>Outputtyper</dt><dd><code>text</code></dd></div><div><dt>Kontekst</dt><dd>262.144 tokens</dd></div><div><dt>Maksimalt output</dt><dd>32.768 tokens</dd></div><div><dt>Outputformat</dt><dd>json eller SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Felt</th><th>Type</th><th>Krav</th><th>Værdier og grænser</th><th>Standard</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>nvidia/nemotron-3.5-lightning-30b-a3b</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>message[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimumsantal elementer: 1</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>user, assistant</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|content_block[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|content_block[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div>Grænsen gælder for: den præcise øvre grænse for valgt model/modelkort</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"known\"><span class=\"card-cell-label\">Standard</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>tool[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: værktøj angivet</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>JSON_schema</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Kombinationer af inputmaterialer</summary><p class=\"note-s\"><b>Tekst</b> · UTF8-tekst</p><p class=\"note-s\"><code>messages[].content eller en blok med type=text</code></p></details><details class=\"note-s\" data-method-contract><summary>Metodeparametre og livscyklus</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Kontrakt</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>required</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>optional_controls</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>null</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>application/json</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>text_file_material</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse</td></tr></tbody></table></div><p>Livscyklus: <code>exact retained published method</code></p><p class=\"note-s\">Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Priser</h3><h4>Ailoot-metodetakster</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>Input</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Output</dt><dd>0,0002 US$ <em>/ 1K</em></dd></div><div><dt>Cachelæsning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning, 5 min.</dt><dd>0,00008 US$ <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailoot reserverer et estimeret beløb før en anmodning. Efter resultatet afregnes det endelige beløb ud fra det målte forbrug. Ved streaming bruges den endelige forbrugsregistrering til afregningen. <a href=\"/docs/da/billing/reserve/\">Sådan fungerer reservation og afregning →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Eksempelanmodninger</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kodevarianter\"><button class=\"cg-tab\" id=\"model-code-553-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-553-panel-0\" aria-selected=\"true\" tabindex=\"0\">Teksteksempel</button><button class=\"cg-tab\" id=\"model-code-553-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-553-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-553-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-553-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-553-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-553-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python-stream</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiér kode\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-553-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-553-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;nvidia/nemotron-3.5-lightning-30b-a3b&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-553-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-553-tab-1\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;nvidia/nemotron-3.5-lightning-30b-a3b&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-553-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-553-tab-2\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;nvidia/nemotron-3.5-lightning-30b-a3b&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-553-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-553-tab-3\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;nvidia/nemotron-3.5-lightning-30b-a3b&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Hent og gem resultater</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json eller SSE</p><div class=\"card-result-process\" data-all-results><h5>Behold alle færdige resultater</h5><p class=\"note-s\">Gem hvert fuldstændigt returneret svar, hver fil og hver indholdsdel.</p><p class=\"note-s\">Bevar alle indholdsblokke, ræsonnementssignaturer og faktiske værktøjsbrugs-ID’er. Saml alle SSE-blokdeltaer; den første tekstblok er ikke hele outputtet.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Hvis det oprindelige svar skal kontrolleres</h5><p class=\"note-s\">Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob.</p></div><details class=\"card-about\" data-output-fields><summary>Svarfelter</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Felt</th><th>Type</th></tr></thead><tbody><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Fejl og næste trin</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Svar</th><th>Betingelse</th><th>Næste trin</th></tr></thead><tbody><tr><th data-cell-label=\"Svar\" scope=\"row\"><span class=\"card-cell-label\">Svar</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Betingelse\"><span class=\"card-cell-label\">Betingelse</span>Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi</td><td data-cell-label=\"Næste trin\"><span class=\"card-cell-label\">Næste trin</span>Ret de angivne felter før en ny oprettelsesanmodning.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Aliaser</h3><h4>Modelaliaser</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=messages\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest\"><code>nemotron-lightning-latest</code></a></span></p><h4>Aliaser for metodestier</h4><p class=\"note-s\">Brug metodestierne vist ovenfor.</p><h4>Relaterede kalder-ID’er</h4><p class=\"note-s\"><a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=messages\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest\"><code>nemotron-lightning-latest</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|nvidia%2Fnemotron-3.5-lightning-30b-a3b",
      "ordinal": 0,
      "rawMethod": {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content eller en blok med type=text",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar alle indholdsblokke, ræsonnementssignaturer og faktiske værktøjsbrugs-ID’er. Saml alle SSE-blokdeltaer; den første tekstblok er ikke hele outputtet.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nvidia/nemotron-3.5-lightning-30b-a3b"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "den præcise øvre grænse for valgt model/modelkort",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "værktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 262144,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/nemotron-3.5-lightning-30b-a3b\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"nvidia/nemotron-3.5-lightning-30b-a3b\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"nvidia/nemotron-3.5-lightning-30b-a3b\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='nvidia/nemotron-3.5-lightning-30b-a3b',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": 32768,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">NV</span><h2 id=\"sheet-title\">Nemotron 3.5 Lightning 30B A3B</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Luk\">×</button></div><div class=\"idline\"><span>NVIDIA /</span><code>nvidia/nemotron-3.5-lightning-30b-a3b</code><button type=\"button\" id=\"copy-id\">Kopiér ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Modelkortets afsnit\"><button type=\"button\" data-card-jump=\"overview\">Start</button><button type=\"button\" data-card-jump=\"methods\">Input og metoder</button><button type=\"button\" data-card-jump=\"pricing\">Priser</button><button type=\"button\" data-card-jump=\"examples\">Eksempler</button><button type=\"button\" data-card-jump=\"results\">Resultater</button><button type=\"button\" data-card-jump=\"aliases\">Aliaser</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API-metoder\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">Messages</button></div><div class=\"idline\"><label for=\"card-model-id\">Model-ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-lightning-30b-a3b\" selected>nvidia/nemotron-3.5-lightning-30b-a3b</option><option value=\"Core|chat|/v1/chat/completions|nemotron-lightning\">nemotron-lightning</option><option value=\"Core|chat|/v1/chat/completions|nemotron-lightning-latest\">nemotron-lightning-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Start</h3><p class=\"mdesc-full\">Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog.</p><dl class=\"card-io\" data-card-io><div><dt>Accepterede input</dt><dd>Tekst</dd></div><div><dt>Resultater</dt><dd>Tekst</dd></div></dl><details class=\"card-about\"><summary>Om modellen</summary><p class=\"note-s\" data-model-method-boundary>Denne beskrivelse dækker modellens funktioner. Tilgængelige input, output og indstillinger i Ailoot står nedenfor for den valgte metode.</p><div class=\"mabout\" id=\"m-about\"><h4>Arbejdsmodel til lange processer</h4><p>Nemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.</p><h4>Arkitektur og kontekst</h4><p>Den hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.</p><p>Lag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.</p><h4>Fem forberedelsestrin</h4><ol><li>Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.</li><li>Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.</li><li>Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.</li><li>Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.</li><li>Efterfølgende numerisk komprimering af den offentliggjorte variant.</li></ol><p>Det sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.</p><h4>Sprog og versioner</h4><p>Engelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.</p><p>Egenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tilgængelig i Ailoot · input og metoder</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>Inputtyper</dt><dd><code>text</code></dd></div><div><dt>Outputtyper</dt><dd><code>text</code></dd></div><div><dt>Kontekst</dt><dd>4.096 tokens</dd></div><div><dt>Maksimalt output</dt><dd>1.024 tokens</dd></div><div><dt>Outputformat</dt><dd>json eller SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Felt</th><th>Type</th><th>Krav</th><th>Værdier og grænser</th><th>Standard</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>nvidia/nemotron-3.5-lightning-30b-a3b</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>message[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimumsantal elementer: 1</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Eksempler: system, user, assistant, tool, function</div><div>Betingelser: Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|content_part[]|null</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>tool_call[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: role=tool; brug det faktisk returnerede ID</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object|array</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"known\"><span class=\"card-cell-label\">Standard</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|string[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>function_tool[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: funktionsværktøj angivet</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>JSON_schema</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Kompatibilitetsfelt</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>function[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Kombinationer af inputmaterialer</summary><p class=\"note-s\"><b>Tekst</b> · UTF8-tekst</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>Metodeparametre og livscyklus</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Kontrakt</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>required</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>model, messages</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>optional_controls</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>null</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>application/json</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>text_file_material</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse</td></tr></tbody></table></div><p>Livscyklus: <code>exact retained published method</code></p><p class=\"note-s\">Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Priser</h3><h4>Ailoot-metodetakster</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>Input</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Output</dt><dd>0,0002 US$ <em>/ 1K</em></dd></div><div><dt>Cachelæsning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning, 5 min.</dt><dd>0,00008 US$ <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailoot reserverer et estimeret beløb før en anmodning. Efter resultatet afregnes det endelige beløb ud fra det målte forbrug. Ved streaming bruges den endelige forbrugsregistrering til afregningen. <a href=\"/docs/da/billing/reserve/\">Sådan fungerer reservation og afregning →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Eksempelanmodninger</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kodevarianter\"><button class=\"cg-tab\" id=\"model-code-554-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-554-panel-0\" aria-selected=\"true\" tabindex=\"0\">Teksteksempel</button><button class=\"cg-tab\" id=\"model-code-554-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-554-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-554-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-554-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-554-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-554-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python-stream</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiér kode\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-554-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-554-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;nvidia/nemotron-3.5-lightning-30b-a3b&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-554-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-554-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;nvidia/nemotron-3.5-lightning-30b-a3b&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-554-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-554-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;nvidia/nemotron-3.5-lightning-30b-a3b&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-554-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-554-tab-3\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;nvidia/nemotron-3.5-lightning-30b-a3b&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Hent og gem resultater</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json eller SSE</p><div class=\"card-result-process\" data-all-results><h5>Behold alle færdige resultater</h5><p class=\"note-s\">Gem hvert fuldstændigt returneret svar, hver fil og hver indholdsdel.</p><p class=\"note-s\">Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Hvis det oprindelige svar skal kontrolleres</h5><p class=\"note-s\">Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob.</p></div><details class=\"card-about\" data-output-fields><summary>Svarfelter</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Felt</th><th>Type</th></tr></thead><tbody><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>integer</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>tool_call[]</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object|array</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Fejl og næste trin</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Svar</th><th>Betingelse</th><th>Næste trin</th></tr></thead><tbody><tr><th data-cell-label=\"Svar\" scope=\"row\"><span class=\"card-cell-label\">Svar</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Betingelse\"><span class=\"card-cell-label\">Betingelse</span>Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi</td><td data-cell-label=\"Næste trin\"><span class=\"card-cell-label\">Næste trin</span>Ret de angivne felter før en ny oprettelsesanmodning.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Aliaser</h3><h4>Modelaliaser</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=chat\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning&amp;fmt=chat\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest&amp;fmt=chat\"><code>nemotron-lightning-latest</code></a></span></p><h4>Aliaser for metodestier</h4><p class=\"note-s\">Brug metodestierne vist ovenfor.</p><h4>Relaterede kalder-ID’er</h4><p class=\"note-s\"><a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=chat\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning&amp;fmt=chat\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest&amp;fmt=chat\"><code>nemotron-lightning-latest</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-lightning-30b-a3b",
      "ordinal": 1,
      "rawMethod": {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nvidia/nemotron-3.5-lightning-30b-a3b"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool; brug det faktisk returnerede ID"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "funktionsværktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/nemotron-3.5-lightning-30b-a3b\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"nvidia/nemotron-3.5-lightning-30b-a3b\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"nvidia/nemotron-3.5-lightning-30b-a3b\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='nvidia/nemotron-3.5-lightning-30b-a3b',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">NV</span><h2 id=\"sheet-title\">Nemotron 3.5 Lightning 30B A3B</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Luk\">×</button></div><div class=\"idline\"><span>NVIDIA /</span><code>nemotron-lightning</code><button type=\"button\" id=\"copy-id\">Kopiér ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Modelkortets afsnit\"><button type=\"button\" data-card-jump=\"overview\">Start</button><button type=\"button\" data-card-jump=\"methods\">Input og metoder</button><button type=\"button\" data-card-jump=\"pricing\">Priser</button><button type=\"button\" data-card-jump=\"examples\">Eksempler</button><button type=\"button\" data-card-jump=\"results\">Resultater</button><button type=\"button\" data-card-jump=\"aliases\">Aliaser</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API-metoder\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|nemotron-lightning\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">Messages</button></div><div class=\"idline\"><label for=\"card-model-id\">Model-ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">nvidia/nemotron-3.5-lightning-30b-a3b</option><option value=\"Core|chat|/v1/chat/completions|nemotron-lightning\" selected>nemotron-lightning</option><option value=\"Core|chat|/v1/chat/completions|nemotron-lightning-latest\">nemotron-lightning-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Start</h3><p class=\"mdesc-full\">Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog.</p><dl class=\"card-io\" data-card-io><div><dt>Accepterede input</dt><dd>Tekst</dd></div><div><dt>Resultater</dt><dd>Tekst</dd></div></dl><details class=\"card-about\"><summary>Om modellen</summary><p class=\"note-s\" data-model-method-boundary>Denne beskrivelse dækker modellens funktioner. Tilgængelige input, output og indstillinger i Ailoot står nedenfor for den valgte metode.</p><div class=\"mabout\" id=\"m-about\"><h4>Arbejdsmodel til lange processer</h4><p>Nemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.</p><h4>Arkitektur og kontekst</h4><p>Den hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.</p><p>Lag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.</p><h4>Fem forberedelsestrin</h4><ol><li>Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.</li><li>Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.</li><li>Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.</li><li>Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.</li><li>Efterfølgende numerisk komprimering af den offentliggjorte variant.</li></ol><p>Det sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.</p><h4>Sprog og versioner</h4><p>Engelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.</p><p>Egenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tilgængelig i Ailoot · input og metoder</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>Inputtyper</dt><dd><code>text</code></dd></div><div><dt>Outputtyper</dt><dd><code>text</code></dd></div><div><dt>Kontekst</dt><dd>4.096 tokens</dd></div><div><dt>Maksimalt output</dt><dd>1.024 tokens</dd></div><div><dt>Outputformat</dt><dd>json eller SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Felt</th><th>Type</th><th>Krav</th><th>Værdier og grænser</th><th>Standard</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>nemotron-lightning</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>message[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimumsantal elementer: 1</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Eksempler: system, user, assistant, tool, function</div><div>Betingelser: Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|content_part[]|null</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>tool_call[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: role=tool; brug det faktisk returnerede ID</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object|array</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"known\"><span class=\"card-cell-label\">Standard</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|string[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>function_tool[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: funktionsværktøj angivet</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>JSON_schema</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Kompatibilitetsfelt</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>function[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Kombinationer af inputmaterialer</summary><p class=\"note-s\"><b>Tekst</b> · UTF8-tekst</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>Metodeparametre og livscyklus</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Kontrakt</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>required</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>model, messages</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>optional_controls</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>null</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>application/json</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>text_file_material</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse</td></tr></tbody></table></div><p>Livscyklus: <code>exact retained published method</code></p><p class=\"note-s\">Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Priser</h3><h4>Ailoot-metodetakster</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>Input</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Output</dt><dd>0,0002 US$ <em>/ 1K</em></dd></div><div><dt>Cachelæsning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning, 5 min.</dt><dd>0,00008 US$ <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailoot reserverer et estimeret beløb før en anmodning. Efter resultatet afregnes det endelige beløb ud fra det målte forbrug. Ved streaming bruges den endelige forbrugsregistrering til afregningen. <a href=\"/docs/da/billing/reserve/\">Sådan fungerer reservation og afregning →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Eksempelanmodninger</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kodevarianter\"><button class=\"cg-tab\" id=\"model-code-555-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-555-panel-0\" aria-selected=\"true\" tabindex=\"0\">Teksteksempel</button><button class=\"cg-tab\" id=\"model-code-555-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-555-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-555-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-555-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-555-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-555-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python-stream</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiér kode\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-555-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-555-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;nemotron-lightning&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-555-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-555-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;nemotron-lightning&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-555-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-555-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;nemotron-lightning&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-555-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-555-tab-3\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;nemotron-lightning&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Hent og gem resultater</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json eller SSE</p><div class=\"card-result-process\" data-all-results><h5>Behold alle færdige resultater</h5><p class=\"note-s\">Gem hvert fuldstændigt returneret svar, hver fil og hver indholdsdel.</p><p class=\"note-s\">Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Hvis det oprindelige svar skal kontrolleres</h5><p class=\"note-s\">Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob.</p></div><details class=\"card-about\" data-output-fields><summary>Svarfelter</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Felt</th><th>Type</th></tr></thead><tbody><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>integer</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>tool_call[]</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object|array</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Fejl og næste trin</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Svar</th><th>Betingelse</th><th>Næste trin</th></tr></thead><tbody><tr><th data-cell-label=\"Svar\" scope=\"row\"><span class=\"card-cell-label\">Svar</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Betingelse\"><span class=\"card-cell-label\">Betingelse</span>Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi</td><td data-cell-label=\"Næste trin\"><span class=\"card-cell-label\">Næste trin</span>Ret de angivne felter før en ny oprettelsesanmodning.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Aliaser</h3><h4>Modelaliaser</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=chat\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning&amp;fmt=chat\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest&amp;fmt=chat\"><code>nemotron-lightning-latest</code></a></span></p><h4>Aliaser for metodestier</h4><p class=\"note-s\">Brug metodestierne vist ovenfor.</p><h4>Relaterede kalder-ID’er</h4><p class=\"note-s\"><a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=chat\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning&amp;fmt=chat\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest&amp;fmt=chat\"><code>nemotron-lightning-latest</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "nemotron-lightning",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "nemotron-lightning",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|nemotron-lightning",
      "ordinal": 2,
      "rawMethod": {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nemotron-lightning"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool; brug det faktisk returnerede ID"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "funktionsværktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-lightning\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"nemotron-lightning\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"nemotron-lightning\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='nemotron-lightning',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nemotron-lightning",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">NV</span><h2 id=\"sheet-title\">Nemotron 3.5 Lightning 30B A3B</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Luk\">×</button></div><div class=\"idline\"><span>NVIDIA /</span><code>nemotron-lightning-latest</code><button type=\"button\" id=\"copy-id\">Kopiér ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Modelkortets afsnit\"><button type=\"button\" data-card-jump=\"overview\">Start</button><button type=\"button\" data-card-jump=\"methods\">Input og metoder</button><button type=\"button\" data-card-jump=\"pricing\">Priser</button><button type=\"button\" data-card-jump=\"examples\">Eksempler</button><button type=\"button\" data-card-jump=\"results\">Resultater</button><button type=\"button\" data-card-jump=\"aliases\">Aliaser</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API-metoder\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|nemotron-lightning-latest\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">Messages</button></div><div class=\"idline\"><label for=\"card-model-id\">Model-ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-lightning-30b-a3b\">nvidia/nemotron-3.5-lightning-30b-a3b</option><option value=\"Core|chat|/v1/chat/completions|nemotron-lightning\">nemotron-lightning</option><option value=\"Core|chat|/v1/chat/completions|nemotron-lightning-latest\" selected>nemotron-lightning-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Start</h3><p class=\"mdesc-full\">Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog.</p><dl class=\"card-io\" data-card-io><div><dt>Accepterede input</dt><dd>Tekst</dd></div><div><dt>Resultater</dt><dd>Tekst</dd></div></dl><details class=\"card-about\"><summary>Om modellen</summary><p class=\"note-s\" data-model-method-boundary>Denne beskrivelse dækker modellens funktioner. Tilgængelige input, output og indstillinger i Ailoot står nedenfor for den valgte metode.</p><div class=\"mabout\" id=\"m-about\"><h4>Arbejdsmodel til lange processer</h4><p>Nemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.</p><h4>Arkitektur og kontekst</h4><p>Den hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.</p><p>Lag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.</p><h4>Fem forberedelsestrin</h4><ol><li>Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.</li><li>Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.</li><li>Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.</li><li>Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.</li><li>Efterfølgende numerisk komprimering af den offentliggjorte variant.</li></ol><p>Det sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.</p><h4>Sprog og versioner</h4><p>Engelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.</p><p>Egenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tilgængelig i Ailoot · input og metoder</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>Inputtyper</dt><dd><code>text</code></dd></div><div><dt>Outputtyper</dt><dd><code>text</code></dd></div><div><dt>Kontekst</dt><dd>4.096 tokens</dd></div><div><dt>Maksimalt output</dt><dd>1.024 tokens</dd></div><div><dt>Outputformat</dt><dd>json eller SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Felt</th><th>Type</th><th>Krav</th><th>Værdier og grænser</th><th>Standard</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>nemotron-lightning-latest</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>message[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimumsantal elementer: 1</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Eksempler: system, user, assistant, tool, function</div><div>Betingelser: Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|content_part[]|null</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>tool_call[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: role=tool; brug det faktisk returnerede ID</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object|array</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Minimum: 1</div><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"known\"><span class=\"card-cell-label\">Standard</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|string[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>function_tool[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Påkrævet</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div>Gælder når: funktionsværktøj angivet</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>JSON_schema</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Kompatibilitetsfelt</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>function[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valgfrit</td><td data-cell-label=\"Værdier og grænser\"><span class=\"card-cell-label\">Værdier og grænser</span><div class=\"note-s\">Afhænger af modellen</div></td><td data-cell-label=\"Standard\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standard</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Kombinationer af inputmaterialer</summary><p class=\"note-s\"><b>Tekst</b> · UTF8-tekst</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>Metodeparametre og livscyklus</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Kontrakt</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>required</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>model, messages</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>optional_controls</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>null</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>application/json</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>text_file_material</code></th><td data-cell-label=\"Kontrakt\"><span class=\"card-cell-label\">Kontrakt</span>faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse</td></tr></tbody></table></div><p>Livscyklus: <code>exact retained published method</code></p><p class=\"note-s\">Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Priser</h3><h4>Ailoot-metodetakster</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>Input</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Output</dt><dd>0,0002 US$ <em>/ 1K</em></dd></div><div><dt>Cachelæsning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning</dt><dd>0,00008 US$ <em>/ 1K</em></dd></div><div><dt>Cacheskrivning, 5 min.</dt><dd>0,00008 US$ <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailoot reserverer et estimeret beløb før en anmodning. Efter resultatet afregnes det endelige beløb ud fra det målte forbrug. Ved streaming bruges den endelige forbrugsregistrering til afregningen. <a href=\"/docs/da/billing/reserve/\">Sådan fungerer reservation og afregning →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Eksempelanmodninger</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kodevarianter\"><button class=\"cg-tab\" id=\"model-code-556-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-556-panel-0\" aria-selected=\"true\" tabindex=\"0\">Teksteksempel</button><button class=\"cg-tab\" id=\"model-code-556-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-556-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-556-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-556-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-556-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-556-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python-stream</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiér kode\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-556-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-556-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;nemotron-lightning-latest&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-556-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-556-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;nemotron-lightning-latest&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-556-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-556-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;nemotron-lightning-latest&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-556-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-556-tab-3\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;nemotron-lightning-latest&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Hent og gem resultater</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json eller SSE</p><div class=\"card-result-process\" data-all-results><h5>Behold alle færdige resultater</h5><p class=\"note-s\">Gem hvert fuldstændigt returneret svar, hver fil og hver indholdsdel.</p><p class=\"note-s\">Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Hvis det oprindelige svar skal kontrolleres</h5><p class=\"note-s\">Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob.</p></div><details class=\"card-about\" data-output-fields><summary>Svarfelter</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Felt</th><th>Type</th></tr></thead><tbody><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>integer</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>tool_call[]</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object|array</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string|null</td></tr><tr><th data-cell-label=\"Felt\" scope=\"row\"><span class=\"card-cell-label\">Felt</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Fejl og næste trin</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Svar</th><th>Betingelse</th><th>Næste trin</th></tr></thead><tbody><tr><th data-cell-label=\"Svar\" scope=\"row\"><span class=\"card-cell-label\">Svar</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Betingelse\"><span class=\"card-cell-label\">Betingelse</span>Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi</td><td data-cell-label=\"Næste trin\"><span class=\"card-cell-label\">Næste trin</span>Ret de angivne felter før en ny oprettelsesanmodning.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Aliaser</h3><h4>Modelaliaser</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=chat\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning&amp;fmt=chat\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest&amp;fmt=chat\"><code>nemotron-lightning-latest</code></a></span></p><h4>Aliaser for metodestier</h4><p class=\"note-s\">Brug metodestierne vist ovenfor.</p><h4>Relaterede kalder-ID’er</h4><p class=\"note-s\"><a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;fmt=chat\"><code>nvidia/nemotron-3.5-lightning-30b-a3b</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning&amp;fmt=chat\"><code>nemotron-lightning</code></a>, <a href=\"#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&amp;route=Core&amp;caller=nemotron-lightning-latest&amp;fmt=chat\"><code>nemotron-lightning-latest</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "nemotron-lightning-latest",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "nemotron-lightning-latest",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|nemotron-lightning-latest",
      "ordinal": 3,
      "rawMethod": {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nemotron-lightning-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool; brug det faktisk returnerede ID"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "funktionsværktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-lightning-latest\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"nemotron-lightning-latest\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"nemotron-lightning-latest\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='nemotron-lightning-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nemotron-lightning-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    }
  ],
  "model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "a0b83a5ed59f2a244d1397afd96707e1a4174e0358555aca166e336b91228bf6",
    "input_html_sha256": "1267ede0d2185763842b5928ecc9aa5017217500ca92586a5013bdbcd5ec33a1",
    "private_audit_sha256": "fd2ed01b8c6443b27d8ad90985d57f72c9ca557d9f4cc067b96f5531f0573cb3",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/da/nvidia-nemotron-3-5-lightning-30b-a3b/",
    "description": "Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog.",
    "locale": "da",
    "md_url": "https://ailoot.ai/models/da/nvidia-nemotron-3-5-lightning-30b-a3b/index.md",
    "title": "Nemotron 3.5 Lightning 30B A3B — Ailoot",
    "url": "https://ailoot.ai/models/da/nvidia-nemotron-3-5-lightning-30b-a3b/"
  },
  "practicalHtml": "<h3>Praktisk opgave</h3><p>Teknisk eksempel på engelsk</p><pre><code>Apply a document-grounded procedure\n\nUse these procedure excerpts to draft the next action for case C-09. [Rule 1] Packages with a damaged seal go to inspection. [Rule 2] Only inspection-cleared packages enter stock. [Record] C-09 has a damaged seal and no inspection result. Return the current permitted step, blocked step and supporting rule labels.</code></pre><h4>Forventet resultat</h4><pre><code>Three concise fields covering the permitted inspection step, blocked stocking and source evidence.</code></pre><h4>Kontrollér resultatet</h4><pre><code>Check that missing inspection clearance prevents stocking and does not become an assumed failed inspection.</code></pre>",
  "practicalText": "Praktisk opgave Teknisk eksempel på engelsk Apply a document-grounded procedure Use these procedure excerpts to draft the next action for case C-09. [Rule 1] Packages with a damaged seal go to inspection. [Rule 2] Only inspection-cleared packages enter stock. [Record] C-09 has a damaged seal and no inspection result. Return the current permitted step, blocked step and supporting rule labels. Forventet resultat Three concise fields covering the permitted inspection step, blocked stocking and source evidence. Kontrollér resultatet Check that missing inspection clearance prevents stocking and does not become an assumed failed inspection.",
  "rawModel": {
    "about": "### Arbejdsmodel til lange processer\n\nNemotron 3.5 Lightning er beregnet til autonome agenter og handlingsforløb i flere trin. Den bruges også til dialogassistenter, dokumentbaseret søgning og instruktionsefterlevelse. Input og output er tekst.\n\n### Arkitektur og kontekst\n\nDen hybride blanding af eksperter kombinerer Mamba-2 og særskilte attentionlag. Modellen har i alt 30 milliarder parametre og 3 milliarder aktive pr. token. Konteksten når en million tokens.\n\nLag, der forudsiger flere efterfølgende tokens, trænes yderligere til at tilpasse forslagene til hovedmodellens fordeling. Udgivelsen ledsages af metoder til spekulativ dekodning. De organiserer genereringen, men fastlægger ikke en garanteret forespørgselshastighed.\n\n### Fem forberedelsestrin\n\n1. Fortræning på mere end 20 billioner tokens fra kode, matematik, videnskab og generel viden i NVFP4-format.\n2. Fortsat fortræning af lag, der forudsiger flere kommende tokens: forslagene tilpasses hovedmodellens fordeling.\n3. Læring fra eksempler med instruktioner, værktøjskald, strukturerede resultater, søgning efter fjerne afsnit og dokumentkombination.\n4. Reinforcement learning i flere miljøer til ræsonnement, kode, videnskab, værktøjsopgaver i flere trin og dialog.\n5. Efterfølgende numerisk komprimering af den offentliggjorte variant.\n\nDet sidste trin beskriver producentens konkrete udgivelse og fastlægger ikke beregningspræcisionen i den betjente forespørgsel. I eksterne processer foreslår modellen handlinger og tekstresultater; applikationen udfører værktøjerne.\n\n### Sprog og versioner\n\nEngelsk, spansk, fransk, tysk, italiensk og japansk samt programmeringssprog er officielt angivet. Dataskæringen for fortræning er september 2025 og for eftertræning maj 2026.\n\nEgenskaberne ved den offentliggjorte numerisk komprimerede udgivelse beskriver netop den variant. Modelnavnet angiver ikke beregningspræcisionen i en konkret kørsel. En million tokens er den samlede kontekst, ikke et særskilt løfte om outputlængde.",
    "alias_of": null,
    "aliases": [
      "nemotron-lightning",
      "nemotron-lightning-latest"
    ],
    "author": "NVIDIA",
    "ctx": 262144,
    "display_name": "Nemotron 3.5 Lightning 30B A3B",
    "formats": [
      "messages",
      "chat"
    ],
    "id": "nvidia/nemotron-3.5-lightning-30b-a3b",
    "input": [
      "text"
    ],
    "kind": "text",
    "max_out": 32768,
    "methods": [
      {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content eller en blok med type=text",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar alle indholdsblokke, ræsonnementssignaturer og faktiske værktøjsbrugs-ID’er. Saml alle SSE-blokdeltaer; den første tekstblok er ikke hele outputtet.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nvidia/nemotron-3.5-lightning-30b-a3b"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "den præcise øvre grænse for valgt model/modelkort",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "værktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 262144,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/nemotron-3.5-lightning-30b-a3b\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"nvidia/nemotron-3.5-lightning-30b-a3b\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"nvidia/nemotron-3.5-lightning-30b-a3b\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='nvidia/nemotron-3.5-lightning-30b-a3b',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": 32768,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nvidia/nemotron-3.5-lightning-30b-a3b"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool; brug det faktisk returnerede ID"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "funktionsværktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/nemotron-3.5-lightning-30b-a3b\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"nvidia/nemotron-3.5-lightning-30b-a3b\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"nvidia/nemotron-3.5-lightning-30b-a3b\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='nvidia/nemotron-3.5-lightning-30b-a3b',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nemotron-lightning"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool; brug det faktisk returnerede ID"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "funktionsværktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-lightning\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"nemotron-lightning\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"nemotron-lightning\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='nemotron-lightning',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nemotron-lightning",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.08,
        "cache_write": 0.08,
        "cache_write_1h": null,
        "cache_write_5m": 0.08,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ugyldige obligatoriske felter, materialerepræsentation eller parameterværdi",
                "http_status": 400,
                "recovery": "Ret de angivne felter før en ny oprettelsesanmodning.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Bevar anmodnings-/svar-ID’er og headere. Der leveres ingen generel URL til at hente tekstjob."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-tekst"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Bevar hvert valg og dets indhold, værktøjskald og ræsonnement. Saml i SSE deltaer efter valg-/værktøjsindeks, og bevar den endelige afslutningsårsag og forbrugsoplysningerne.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json eller SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "nemotron-lightning-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "Disse roller er eksplicit repræsenteret i kildekodens kompatibilitetstyper; modellens præcise rollesæt er fortsat modelspecifikt.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool; brug det faktisk returnerede ID"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "Send det faktisk returnerede ræsonnement tilbage, når modellen bruger det"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "funktionsværktøj angivet"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "Metodernes strukturer og ID’er er præcise; leverandørens muligheder er adskilt fra adgangstilladelse."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "faktisk UTF-8-indhold indsat som tekst; fil-ID’er/URLs kræver særskilt præcis understøttelse"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nemotron-lightning-latest\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"nemotron-lightning-latest\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"nemotron-lightning-latest\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='nemotron-lightning-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.08,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.2,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.2,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.08,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "nemotron-lightning-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "request_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "request_model_id": "nemotron-lightning",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b",
        "request_model_id": "nemotron-lightning-latest",
        "route_label": "Core"
      }
    ],
    "name": "nvidia/nemotron-3.5-lightning-30b-a3b",
    "price": {
      "in": 0.08,
      "in_label": null,
      "out": 0.2,
      "out_label": null,
      "sort_in": 0.08,
      "sort_out": 0.2,
      "varies": false
    },
    "short": "Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog."
  },
  "renderer_schema": {
    "method_order": "Original DTO methods order; every exact route/format/path/caller survives.",
    "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers."
  },
  "representation": "exact-public-dto-and-native-renderer-html",
  "representationNotes": {
    "current_reference": {
      "about_json_pointer": "/aboutHtml",
      "methods": [
        {
          "contract_json_pointer": "/methods/0/rawMethod/contract",
          "html_json_pointer": "/methods/0/html",
          "method_ordinal": 0
        },
        {
          "contract_json_pointer": "/methods/1/rawMethod/contract",
          "html_json_pointer": "/methods/1/html",
          "method_ordinal": 1
        },
        {
          "contract_json_pointer": "/methods/2/rawMethod/contract",
          "html_json_pointer": "/methods/2/html",
          "method_ordinal": 2
        },
        {
          "contract_json_pointer": "/methods/3/rawMethod/contract",
          "html_json_pointer": "/methods/3/html",
          "method_ordinal": 3
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod",
        "/methods/1/rawMethod",
        "/methods/2/rawMethod",
        "/methods/3/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "Nemotron 3.5 Lightning er en tekstmodel fra NVIDIA til lange agentopgaver, programmering, dokumentsøgning og dialog.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "acca6276fc1fe58e6b7464c17ea7ba30279de17332fd560e17d30e1d7de56049",
    "renderer_sha256": "2bf9f26ea9bfd57ed53d867671d8f05b41a6ea85089f48039e3365dc2b92ec2c"
  },
  "sourceRevision": "e626b3e1f358a8367549305b62e08cb6d2c6eff3642285d1106ec5f08523a31b"
}
