{
  "aboutHtml": "<p>DeepSeek V3.1 Terminus är DeepSeeks uppdatering av textmodellprofilen V3.1. Den behåller de ursprungliga förmågorna och hanterar samtidigt oönskad blandning av kinesiska och engelska, enstaka avvikande tecken och beteendet hos kod- och sökagenter. Indata är en skriftlig uppgift och källkontext; utdata är text, som kan innehålla en förklaring, föreslagen kod eller agentrelaterat innehåll. Den namngivna Terminus-utgåvan förblir separat från ursprungliga V3.1 och senare utgåvor med gles attention.</p><p>Den ärvda V3.1-profilen är hybrid: en modell kan svara i läge med eller utan tänkande genom sin chattmall. V3.1:s publicerade modelltabell anger totalt 671 miljarder parametrar, 37 miljarder aktiva parametrar och en kontext på 128K. Terminus beskriver samma modellstruktur som V3 och hänvisar till V3.1 för konversationsmallen utanför det reviderade arbetsflödet för sökagenten. Dessa referenser kopplar uppdateringen till den underliggande familjen och bevarar samtidigt dess egna ändringar.</p><p>För en direkt kodningsassistent stöder den ärvda mallen standardverktygsanrop i läget utan tänkande, med namngivna funktioner och JSON-argument baserade på de tillhandahållna verktygsdefinitionerna. Modellen föreslår operationen, applikationen utför den och returnerar observationen. Sökning i tänkandeläge följer ett specialiserat sökagentformat. Terminus uppdaterar sökmallen och verktygsuppsättningen, så sökförloppet ska använda Terminus-referensen snarare än en orelaterad mall från en annan utgåva.</p><p>Språklig konsekvens är en praktisk skillnad mellan utgåvorna. För en dokumentuppgift på kinesiska eller engelska anger du svarsspråket, termerna som måste behålla sin ursprungliga stavning och källavsnitten som ska användas. Ett exempel på uppdragsbeskrivning är: ”Skriv förklaringen på engelska, bevara de tillhandahållna variabelnamnen och undvik att översätta API-fältnamnen. Basera varje iakttagelse på den tillhandahållna specifikationen.” Uppdateringen riktar in sig på oönskad språkväxling, medan din uppdragsbeskrivning fortfarande definierar vilket flerspråkigt material som är avsiktligt.</p><p>Modellen kan använda ett användartillhandahållet sökverktyg för frågor som kräver extern eller aktuell information. Tillhandahåll researchfrågan, kriterierna för användbara källor och slutleveransen. En kodningsuppgift ska innehålla det relevanta fragmentet, observerat beteende och förväntat resultat. Håll verktygsreturer kopplade till den operation som skapade dem och be slutsvaret identifiera beläggen bakom en föreslagen ändring eller slutsats.</p><p>Producenten registrerar en checkpointspecifik precisionsdetalj: parametrarna för attention-utdataprojektionen följer inte skalformatet UE8M0 FP8 som används i V3.1-utgåvan. Det är en aspekt av referensimplementationen, inte en ändring av uppgiftens språk, modalitet eller svarsformat. Det är ett skäl att behålla Terminus som en egen utgåva och undvika att behandla alla V3.1-checkpoints som identiska precisionsprofiler.</p><p>För längre arbete budgeterar du källmaterialet, konversationen och det genererade svaret inom familjekontexten på 128K. Märk dokumentavsnitt och kodfragment så att ett resultat kan hänvisa tillbaka till rätt belägg. I en uppgift med flera steg definierar du de tillåtna åtgärderna, den obligatoriska leveransen och färdigställandekriteriet. Det användbara resultatet är ett konsekvent textsvar, kodförslag eller en källstödd analys som kan granskas mot indata och de faktiska verktygsobservationerna.</p>",
  "aboutText": "DeepSeek V3.1 Terminus är DeepSeeks uppdatering av textmodellprofilen V3.1. Den behåller de ursprungliga förmågorna och hanterar samtidigt oönskad blandning av kinesiska och engelska, enstaka avvikande tecken och beteendet hos kod- och sökagenter. Indata är en skriftlig uppgift och källkontext; utdata är text, som kan innehålla en förklaring, föreslagen kod eller agentrelaterat innehåll. Den namngivna Terminus-utgåvan förblir separat från ursprungliga V3.1 och senare utgåvor med gles attention.\n\nDen ärvda V3.1-profilen är hybrid: en modell kan svara i läge med eller utan tänkande genom sin chattmall. V3.1:s publicerade modelltabell anger totalt 671 miljarder parametrar, 37 miljarder aktiva parametrar och en kontext på 128K. Terminus beskriver samma modellstruktur som V3 och hänvisar till V3.1 för konversationsmallen utanför det reviderade arbetsflödet för sökagenten. Dessa referenser kopplar uppdateringen till den underliggande familjen och bevarar samtidigt dess egna ändringar.\n\nFör en direkt kodningsassistent stöder den ärvda mallen standardverktygsanrop i läget utan tänkande, med namngivna funktioner och JSON-argument baserade på de tillhandahållna verktygsdefinitionerna. Modellen föreslår operationen, applikationen utför den och returnerar observationen. Sökning i tänkandeläge följer ett specialiserat sökagentformat. Terminus uppdaterar sökmallen och verktygsuppsättningen, så sökförloppet ska använda Terminus-referensen snarare än en orelaterad mall från en annan utgåva.\n\nSpråklig konsekvens är en praktisk skillnad mellan utgåvorna. För en dokumentuppgift på kinesiska eller engelska anger du svarsspråket, termerna som måste behålla sin ursprungliga stavning och källavsnitten som ska användas. Ett exempel på uppdragsbeskrivning är: ”Skriv förklaringen på engelska, bevara de tillhandahållna variabelnamnen och undvik att översätta API-fältnamnen. Basera varje iakttagelse på den tillhandahållna specifikationen.” Uppdateringen riktar in sig på oönskad språkväxling, medan din uppdragsbeskrivning fortfarande definierar vilket flerspråkigt material som är avsiktligt.\n\nModellen kan använda ett användartillhandahållet sökverktyg för frågor som kräver extern eller aktuell information. Tillhandahåll researchfrågan, kriterierna för användbara källor och slutleveransen. En kodningsuppgift ska innehålla det relevanta fragmentet, observerat beteende och förväntat resultat. Håll verktygsreturer kopplade till den operation som skapade dem och be slutsvaret identifiera beläggen bakom en föreslagen ändring eller slutsats.\n\nProducenten registrerar en checkpointspecifik precisionsdetalj: parametrarna för attention-utdataprojektionen följer inte skalformatet UE8M0 FP8 som används i V3.1-utgåvan. Det är en aspekt av referensimplementationen, inte en ändring av uppgiftens språk, modalitet eller svarsformat. Det är ett skäl att behålla Terminus som en egen utgåva och undvika att behandla alla V3.1-checkpoints som identiska precisionsprofiler.\n\nFör längre arbete budgeterar du källmaterialet, konversationen och det genererade svaret inom familjekontexten på 128K. Märk dokumentavsnitt och kodfragment så att ett resultat kan hänvisa tillbaka till rätt belägg. I en uppgift med flera steg definierar du de tillåtna åtgärderna, den obligatoriska leveransen och färdigställandekriteriet. Det användbara resultatet är ett konsekvent textsvar, kodförslag eller en källstödd analys som kan granskas mot indata och de faktiska verktygsobservationerna.",
  "editorialOverlay": {
    "copy_fields": {
      "practical_html": "<h3>Praktisk uppgift</h3><p>Tekniskt exempel på engelska</p><pre><code>Explain a field rule in English\n\nWrite an English explanation of this validation rule for an integration guide: &quot;retry_count must be a nonnegative integer; retry_after_ms may be omitted; when present, it must be a positive integer.&quot; Preserve the field names exactly. Add one valid and one invalid example as plain text, explaining the invalid field without translating identifiers.</code></pre><h4>Förväntat resultat</h4><pre><code>An English paragraph plus two labelled examples and a specific validation explanation.</code></pre><h4>Kontrollera resultatet</h4><pre><code>Check that retry_count accepts zero while retry_after_ms does not.</code></pre>"
    },
    "copy_sha256": "448d46b4c4a2ae20b1bd98cd60bc572e86650af95d8198e75224b2940505593f",
    "copy_source": {
      "locale": "sv",
      "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7",
      "record_model_id": "deepseek/deepseek-v3.1-terminus",
      "source_facts_sha256": "0b010aa2b35f974907052d181403c0816eedb5c923db36267c5b1f9754df4aaa",
      "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6"
    },
    "html_sha256": "e6c44f974e0613b1edbea03dd0962083c4e465b7707af5712700f1102971507b",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "sv",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">DS</span><h2 id=\"sheet-title\">DeepSeek: DeepSeek V3.1 Terminus</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Stäng\">×</button></div><div class=\"idline\"><span>DeepSeek /</span><code>deepseek/deepseek-v3.1-terminus</code><button type=\"button\" id=\"copy-id\">Kopiera ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Modellkortets avsnitt\"><button type=\"button\" data-card-jump=\"overview\">Start</button><button type=\"button\" data-card-jump=\"methods\">Indata &amp; metoder</button><button type=\"button\" data-card-jump=\"pricing\">Priser</button><button type=\"button\" data-card-jump=\"examples\">Exempel</button><button type=\"button\" data-card-jump=\"results\">Resultat</button><button type=\"button\" data-card-jump=\"aliases\">Alias</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=\"Ultra|chat|/v1/chat/completions|deepseek%2Fdeepseek-v3.1-terminus\">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=\"Ultra|messages|/v1/messages|deepseek%2Fdeepseek-v3.1-terminus\">Messages</button></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\">DeepSeek V3.1 Terminus förfinar V3.1-textmodellens språkliga konsekvens och beteendet hos kod- och sökagenter. Den behåller hybridprofilen med tänkande och direkta svar, med en kontext på 128K och en uppdaterad sökagentmall som hålls åtskild från senare V3.2-format.</p><dl class=\"card-io\" data-card-io><div><dt>Godkända indata</dt><dd>Text</dd></div><div><dt>Resultat</dt><dd>Text</dd></div></dl><details class=\"card-about\"><summary>Om modellen</summary><p class=\"note-s\" data-model-method-boundary>Den här beskrivningen omfattar modellens förmågor. Tillgängliga indata, utdata och alternativ i Ailoot anges nedan för den valda metoden.</p><div class=\"mabout\" id=\"m-about\"><p>DeepSeek V3.1 Terminus är DeepSeeks uppdatering av textmodellprofilen V3.1. Den behåller de ursprungliga förmågorna och hanterar samtidigt oönskad blandning av kinesiska och engelska, enstaka avvikande tecken och beteendet hos kod- och sökagenter. Indata är en skriftlig uppgift och källkontext; utdata är text, som kan innehålla en förklaring, föreslagen kod eller agentrelaterat innehåll. Den namngivna Terminus-utgåvan förblir separat från ursprungliga V3.1 och senare utgåvor med gles attention.</p><p>Den ärvda V3.1-profilen är hybrid: en modell kan svara i läge med eller utan tänkande genom sin chattmall. V3.1:s publicerade modelltabell anger totalt 671 miljarder parametrar, 37 miljarder aktiva parametrar och en kontext på 128K. Terminus beskriver samma modellstruktur som V3 och hänvisar till V3.1 för konversationsmallen utanför det reviderade arbetsflödet för sökagenten. Dessa referenser kopplar uppdateringen till den underliggande familjen och bevarar samtidigt dess egna ändringar.</p><p>För en direkt kodningsassistent stöder den ärvda mallen standardverktygsanrop i läget utan tänkande, med namngivna funktioner och JSON-argument baserade på de tillhandahållna verktygsdefinitionerna. Modellen föreslår operationen, applikationen utför den och returnerar observationen. Sökning i tänkandeläge följer ett specialiserat sökagentformat. Terminus uppdaterar sökmallen och verktygsuppsättningen, så sökförloppet ska använda Terminus-referensen snarare än en orelaterad mall från en annan utgåva.</p><p>Språklig konsekvens är en praktisk skillnad mellan utgåvorna. För en dokumentuppgift på kinesiska eller engelska anger du svarsspråket, termerna som måste behålla sin ursprungliga stavning och källavsnitten som ska användas. Ett exempel på uppdragsbeskrivning är: ”Skriv förklaringen på engelska, bevara de tillhandahållna variabelnamnen och undvik att översätta API-fältnamnen. Basera varje iakttagelse på den tillhandahållna specifikationen.” Uppdateringen riktar in sig på oönskad språkväxling, medan din uppdragsbeskrivning fortfarande definierar vilket flerspråkigt material som är avsiktligt.</p><p>Modellen kan använda ett användartillhandahållet sökverktyg för frågor som kräver extern eller aktuell information. Tillhandahåll researchfrågan, kriterierna för användbara källor och slutleveransen. En kodningsuppgift ska innehålla det relevanta fragmentet, observerat beteende och förväntat resultat. Håll verktygsreturer kopplade till den operation som skapade dem och be slutsvaret identifiera beläggen bakom en föreslagen ändring eller slutsats.</p><p>Producenten registrerar en checkpointspecifik precisionsdetalj: parametrarna för attention-utdataprojektionen följer inte skalformatet UE8M0 FP8 som används i V3.1-utgåvan. Det är en aspekt av referensimplementationen, inte en ändring av uppgiftens språk, modalitet eller svarsformat. Det är ett skäl att behålla Terminus som en egen utgåva och undvika att behandla alla V3.1-checkpoints som identiska precisionsprofiler.</p><p>För längre arbete budgeterar du källmaterialet, konversationen och det genererade svaret inom familjekontexten på 128K. Märk dokumentavsnitt och kodfragment så att ett resultat kan hänvisa tillbaka till rätt belägg. I en uppgift med flera steg definierar du de tillåtna åtgärderna, den obligatoriska leveransen och färdigställandekriteriet. Det användbara resultatet är ett konsekvent textsvar, kodförslag eller en källstödd analys som kan granskas mot indata och de faktiska verktygsobservationerna.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tillgängligt i Ailoot · indata &amp; metoder</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>Indatatyper</dt><dd><code>text</code></dd></div><div><dt>Utdatatyper</dt><dd><code>text</code></dd></div><div><dt>Utdataformat</dt><dd>json eller SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Fält</th><th>Typ</th><th>Krav</th><th>Värden &amp; gränser</th><th>Standard</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>deepseek/deepseek-v3.1-terminus</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>message[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Minsta antal objekt: 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Exempel: system, user, assistant, tool, function</div><div>Villkor: Dessa roller representeras uttryckligen av källkodens kompatibilitetstyper; den exakta rolluppsättningen är fortfarande modellspecifik.</div><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string|content_part[]|null</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>tool_call[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Gäller när: role=tool; använd det faktiska returnerade ID:t</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Gäller när: Skicka tillbaka det faktiska returnerade resonemanget när modellen använder 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>object|array</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Minimum: 1</div><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Minimum: 1</div><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>number</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string|string[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>function_tool[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>function</div><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Gäller när: verktyg av typen funktion har tillhandahållits</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>JSON_schema</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Kompatibilitetsfält</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>function[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string|object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div class=\"note-s\">Beror på 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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">modalities</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>text</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>object</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Villkor: provider.options avvisas på denna Ultra-textrutt</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">cache_control.ttl</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>Villkor: 1h avvisas på de faktiska platserna för promptcache</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 av indatamaterial</summary><p class=\"note-s\"><b>Text</b> · UTF8-text</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>Metodparametrar och livscykel</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Avtal</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>application/json</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=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>model, messages</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>messages</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>meddelandearray med strukturen role/content</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>file_material</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>det faktiska UTF-8-dokumentet infogat som bokstavlig text; inget fil-ID härleds</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=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>stream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>control_scope</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>modellspecifikt; användarens funktionsverktyg skiljer sig från värdbaserade verktyg</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>output_modalities</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>hosted_operations</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>false</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>multimodal_input_binding</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>null</td></tr></tbody></table></div><p>Livscykel: <code>synchronous_or_streamed</code></p><p class=\"note-s\">Skicka det exakta modell-ID:t tillsammans med messages.</p><p class=\"note-s\">Kontextlängden är inte en utdatagräns.</p><p class=\"note-s\">En textfil kan tillhandahålla bokstavlig text; bild-/ljud-/filobjektsindata kräver exakt bindning.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Priser</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Tariffuppgifter lägger inte till begäransalternativ. Parametrar som stöds anges för den valda metoden.</p><dl data-price-conditions><dt>Snabbt läge</dt><dd>Ej angivet <span class=\"note-s\">När snabbt läge är valt</span></dd><dt>Flex-läge</dt><dd>Ej angivet <span class=\"note-s\">När läget flex är valt</span></dd><dt>Högsta resonemangsnivå</dt><dd>Ej angivet <span class=\"note-s\">När den högsta resonemangsnivån använder standardjusteringen (default)</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot-priser</h4><h4>Priser efter konfiguration</h4><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Konfiguration</th><th>Prislista</th><th>Avgift</th></tr></thead><tbody><tr><th data-cell-label=\"Konfiguration\" scope=\"row\"><span class=\"card-cell-label\">Konfiguration</span>Grundpriser för token</th><td data-cell-label=\"Prislista\"><span class=\"card-cell-label\">Prislista</span>Grundpris</td><td data-cell-label=\"Avgift\"><span class=\"card-cell-label\">Avgift</span><div><span>Indata · Indatatoken</span> <b>$0.001144</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Utdata · Utdatatoken</span> <b>$0.00343</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Indata · Cacheläsning</span> <b>$0</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Indata · Skrivning till cache</span> <b>$0</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Indata · Skrivning till cache, 1 tim</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot reserverar ett uppskattat belopp före en begäran. Efter resultatet slutregleras avgiften utifrån uppmätt förbrukning. Slutreglering för strömning använder den slutliga förbrukningsposten. <a href=\"/docs/sv/billing/reserve/\">Så fungerar reservation och slutreglering →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Exempelbegäranden</h3><h4>Ailoot Ultra · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kodvarianter\"><button class=\"cg-tab\" id=\"model-code-1246-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1246-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-1246-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1246-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-1246-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1246-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python-strömning</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiera kod\"><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-1246-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-1246-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;deepseek/deepseek-v3.1-terminus&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}]}&#39;)\n\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\nr=json.loads(Path(&quot;result.json&quot;).read_text())\nfor x in r.get(&quot;choices&quot;,[]):\n    if x.get(&quot;message&quot;,{}).get(&quot;content&quot;): print(x[&quot;message&quot;][&quot;content&quot;])\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-1246-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-1246-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)\nresult=client.chat.completions.create(model=&#39;deepseek/deepseek-v3.1-terminus&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}])\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(result.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-1246-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-1246-tab-2\" 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;deepseek/deepseek-v3.1-terminus&#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\">Ta emot och spara resultat</h3><h4>Ailoot Ultra · OpenAI Chat</h4><p class=\"note-s\">json eller SSE</p><div class=\"card-result-process\" data-all-results><h5>Behåll alla färdiga resultat</h5><p class=\"note-s\">Behåll varje fullständigt returnerat svar, fil och innehållsdel.</p><p class=\"note-s\">Behåll varje svarsalternativ och dess innehåll/verktygsanrop/resonemang. Sätt i SSE samman deltauppdateringar efter svarsalternativets/verktygets index och behåll den slutliga avslutsorsaken och användningsuppgifterna.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Om det ursprungliga svaret behöver kontrolleras</h5><p class=\"note-s\">Behåll begärans/svarets ID:n och huvuden. Ingen generell URL för hämtning av textjobb tillhandahålls.</p></div><details class=\"card-about\" data-output-fields><summary>Svarsfält</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Fält</th><th>Typ</th></tr></thead><tbody><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>integer</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>string|null</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>tool_call[]</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>string</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>object|array</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>string|null</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Fel och nästa steg</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Svar</th><th>Villkor</th><th>Nästa steg</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=\"Villkor\"><span class=\"card-cell-label\">Villkor</span>Ogiltiga obligatoriska fält, ogiltig representation av underlaget eller ogiltigt parametervärde</td><td data-cell-label=\"Nästa steg\"><span class=\"card-cell-label\">Nästa steg</span>Korrigera de angivna fälten före en ny begäran om att skapa.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Alias</h3><h4>Modellalias</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=deepseek%2Fdeepseek-v3.1-terminus&amp;route=Ultra&amp;caller=deepseek%2Fdeepseek-v3.1-terminus&amp;fmt=chat\"><code>deepseek/deepseek-v3.1-terminus</code></a></span></p><h4>Alias för metodsökvägar</h4><p class=\"note-s\">Använd metodsökvägarna som visas ovan.</p><h4>Relaterade anropar-ID:n</h4><p class=\"note-s\"><a href=\"#m=deepseek%2Fdeepseek-v3.1-terminus&amp;route=Ultra&amp;caller=deepseek%2Fdeepseek-v3.1-terminus&amp;fmt=chat\"><code>deepseek/deepseek-v3.1-terminus</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "deepseek/deepseek-v3.1-terminus",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|chat|/v1/chat/completions|deepseek%2Fdeepseek-v3.1-terminus",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": 0,
        "cache_write": 0,
        "cache_write_1h": 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": "Ogiltiga obligatoriska fält, ogiltig representation av underlaget eller ogiltigt parametervärde",
                "http_status": 400,
                "recovery": "Korrigera de angivna fälten före en ny begäran om att skapa.",
                "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.",
              "Guarded canonical keys must occur once; duplicate or case-varied model/tools/cap fields are rejected."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Behåll begärans/svarets ID:n och huvuden. Ingen generell URL för hämtning av textjobb tillhandahålls."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-text"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Behåll varje svarsalternativ och dess innehåll/verktygsanrop/resonemang. Sätt i SSE samman deltauppdateringar efter svarsalternativets/verktygets index och behåll den slutliga avslutsorsaken och användningsuppgifterna.",
              "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": [
                  "deepseek/deepseek-v3.1-terminus"
                ],
                "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": "Dessa roller representeras uttryckligen av källkodens kompatibilitetstyper; den exakta rolluppsättningen är fortfarande modellspecifik.",
                "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; använd det faktiska returnerade ID:t"
              },
              {
                "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": "Skicka tillbaka det faktiska returnerade resonemanget när modellen använder 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": [
                  "function"
                ],
                "enum_known": true,
                "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": "verktyg av typen funktion har tillhandahållits"
              },
              {
                "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"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "text"
                ],
                "enum_known": true,
                "name": "modalities",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "conditions": "provider.options avvisas på denna Ultra-textrutt",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "conditions": "1h avvisas på de faktiska platserna för promptcache",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control.ttl",
                "required": false,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "Skicka det exakta modell-ID:t tillsammans med messages.",
            "Kontextlängden är inte en utdatagräns.",
            "En textfil kan tillhandahålla bokstavlig text; bild-/ljud-/filobjektsindata kräver exakt bindning."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "modellspecifikt; användarens funktionsverktyg skiljer sig från värdbaserade verktyg",
            "file_material": "det faktiska UTF-8-dokumentet infogat som bokstavlig text; inget fil-ID härleds",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "meddelandearray med strukturen role/content",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream",
              "temperature",
              "top_p",
              "stop",
              "max_tokens",
              "max_completion_tokens",
              "reasoning",
              "response_format",
              "tools",
              "tool_choice"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Grundpriser för token",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"deepseek/deepseek-v3.1-terminus\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}]}')\n\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\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "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)\nresult=client.chat.completions.create(model='deepseek/deepseek-v3.1-terminus',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}])\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(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          },
          {
            "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='deepseek/deepseek-v3.1-terminus',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 SDK streaming · all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 1.144,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 3.43,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">DS</span><h2 id=\"sheet-title\">DeepSeek: DeepSeek V3.1 Terminus</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Stäng\">×</button></div><div class=\"idline\"><span>DeepSeek /</span><code>deepseek/deepseek-v3.1-terminus</code><button type=\"button\" id=\"copy-id\">Kopiera ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Modellkortets avsnitt\"><button type=\"button\" data-card-jump=\"overview\">Start</button><button type=\"button\" data-card-jump=\"methods\">Indata &amp; metoder</button><button type=\"button\" data-card-jump=\"pricing\">Priser</button><button type=\"button\" data-card-jump=\"examples\">Exempel</button><button type=\"button\" data-card-jump=\"results\">Resultat</button><button type=\"button\" data-card-jump=\"aliases\">Alias</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=\"Ultra|chat|/v1/chat/completions|deepseek%2Fdeepseek-v3.1-terminus\">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=\"Ultra|messages|/v1/messages|deepseek%2Fdeepseek-v3.1-terminus\">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\">DeepSeek V3.1 Terminus förfinar V3.1-textmodellens språkliga konsekvens och beteendet hos kod- och sökagenter. Den behåller hybridprofilen med tänkande och direkta svar, med en kontext på 128K och en uppdaterad sökagentmall som hålls åtskild från senare V3.2-format.</p><dl class=\"card-io\" data-card-io><div><dt>Godkända indata</dt><dd>Text</dd></div><div><dt>Resultat</dt><dd>json · sse</dd></div></dl><details class=\"card-about\"><summary>Om modellen</summary><p class=\"note-s\" data-model-method-boundary>Den här beskrivningen omfattar modellens förmågor. Tillgängliga indata, utdata och alternativ i Ailoot anges nedan för den valda metoden.</p><div class=\"mabout\" id=\"m-about\"><p>DeepSeek V3.1 Terminus är DeepSeeks uppdatering av textmodellprofilen V3.1. Den behåller de ursprungliga förmågorna och hanterar samtidigt oönskad blandning av kinesiska och engelska, enstaka avvikande tecken och beteendet hos kod- och sökagenter. Indata är en skriftlig uppgift och källkontext; utdata är text, som kan innehålla en förklaring, föreslagen kod eller agentrelaterat innehåll. Den namngivna Terminus-utgåvan förblir separat från ursprungliga V3.1 och senare utgåvor med gles attention.</p><p>Den ärvda V3.1-profilen är hybrid: en modell kan svara i läge med eller utan tänkande genom sin chattmall. V3.1:s publicerade modelltabell anger totalt 671 miljarder parametrar, 37 miljarder aktiva parametrar och en kontext på 128K. Terminus beskriver samma modellstruktur som V3 och hänvisar till V3.1 för konversationsmallen utanför det reviderade arbetsflödet för sökagenten. Dessa referenser kopplar uppdateringen till den underliggande familjen och bevarar samtidigt dess egna ändringar.</p><p>För en direkt kodningsassistent stöder den ärvda mallen standardverktygsanrop i läget utan tänkande, med namngivna funktioner och JSON-argument baserade på de tillhandahållna verktygsdefinitionerna. Modellen föreslår operationen, applikationen utför den och returnerar observationen. Sökning i tänkandeläge följer ett specialiserat sökagentformat. Terminus uppdaterar sökmallen och verktygsuppsättningen, så sökförloppet ska använda Terminus-referensen snarare än en orelaterad mall från en annan utgåva.</p><p>Språklig konsekvens är en praktisk skillnad mellan utgåvorna. För en dokumentuppgift på kinesiska eller engelska anger du svarsspråket, termerna som måste behålla sin ursprungliga stavning och källavsnitten som ska användas. Ett exempel på uppdragsbeskrivning är: ”Skriv förklaringen på engelska, bevara de tillhandahållna variabelnamnen och undvik att översätta API-fältnamnen. Basera varje iakttagelse på den tillhandahållna specifikationen.” Uppdateringen riktar in sig på oönskad språkväxling, medan din uppdragsbeskrivning fortfarande definierar vilket flerspråkigt material som är avsiktligt.</p><p>Modellen kan använda ett användartillhandahållet sökverktyg för frågor som kräver extern eller aktuell information. Tillhandahåll researchfrågan, kriterierna för användbara källor och slutleveransen. En kodningsuppgift ska innehålla det relevanta fragmentet, observerat beteende och förväntat resultat. Håll verktygsreturer kopplade till den operation som skapade dem och be slutsvaret identifiera beläggen bakom en föreslagen ändring eller slutsats.</p><p>Producenten registrerar en checkpointspecifik precisionsdetalj: parametrarna för attention-utdataprojektionen följer inte skalformatet UE8M0 FP8 som används i V3.1-utgåvan. Det är en aspekt av referensimplementationen, inte en ändring av uppgiftens språk, modalitet eller svarsformat. Det är ett skäl att behålla Terminus som en egen utgåva och undvika att behandla alla V3.1-checkpoints som identiska precisionsprofiler.</p><p>För längre arbete budgeterar du källmaterialet, konversationen och det genererade svaret inom familjekontexten på 128K. Märk dokumentavsnitt och kodfragment så att ett resultat kan hänvisa tillbaka till rätt belägg. I en uppgift med flera steg definierar du de tillåtna åtgärderna, den obligatoriska leveransen och färdigställandekriteriet. Det användbara resultatet är ett konsekvent textsvar, kodförslag eller en källstödd analys som kan granskas mot indata och de faktiska verktygsobservationerna.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tillgängligt i Ailoot · indata &amp; metoder</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>Indatatyper</dt><dd><code>text</code></dd></div><div><dt>Utdatatyper</dt><dd><code>json</code>, <code>sse</code></dd></div><div><dt>Utdataformat</dt><dd>JSON eller SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Fält</th><th>Typ</th><th>Krav</th><th>Värden &amp; gränser</th><th>Standard</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span><div>deepseek/deepseek-v3.1-terminus</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>message[]</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>string</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>integer</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Obligatoriskt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</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=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span><code>boolean</code></td><td data-cell-label=\"Krav\"><span class=\"card-cell-label\">Krav</span>Valfritt</td><td data-cell-label=\"Värden &amp; gränser\"><span class=\"card-cell-label\">Värden &amp; gränser</span></td><td data-cell-label=\"Standard\" data-default=\"known\"><span class=\"card-cell-label\">Standard</span>false</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Kombinationer av indatamaterial</summary><p class=\"note-s\"><b>Text</b> · UTF-8-text</p><p class=\"note-s\"><code>sträng i messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>Metodparametrar och livscykel</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Avtal</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>application/json</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=\"Avtal\"><span class=\"card-cell-label\">Avtal</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=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>stream</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>text</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=\"Avtal\"><span class=\"card-cell-label\">Avtal</span>Läs det faktiska UTF-8-dokumentet och placera texten i det angivna input-fältet eller i strängen för meddelandets innehåll.</td></tr></tbody></table></div><p>Livscykel: <code>synchronous_or_streamed</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Priser</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Tariffuppgifter lägger inte till begäransalternativ. Parametrar som stöds anges för den valda metoden.</p><dl data-price-conditions><dt>Snabbt läge</dt><dd>Ej angivet <span class=\"note-s\">När snabbt läge är valt</span></dd><dt>Flex-läge</dt><dd>Ej angivet <span class=\"note-s\">När läget flex är valt</span></dd><dt>Högsta resonemangsnivå</dt><dd>Ej angivet <span class=\"note-s\">När den högsta resonemangsnivån använder standardjusteringen (default)</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot-priser</h4><h4>Priser efter konfiguration</h4><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Konfiguration</th><th>Prislista</th><th>Avgift</th></tr></thead><tbody><tr><th data-cell-label=\"Konfiguration\" scope=\"row\"><span class=\"card-cell-label\">Konfiguration</span>Grundpriser för token</th><td data-cell-label=\"Prislista\"><span class=\"card-cell-label\">Prislista</span>Grundpris</td><td data-cell-label=\"Avgift\"><span class=\"card-cell-label\">Avgift</span><div><span>Indata · Indatatoken</span> <b>$0.001144</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Utdata · Utdatatoken</span> <b>$0.00343</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Indata · Cacheläsning</span> <b>$0</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Indata · Skrivning till cache</span> <b>$0</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Indata · Skrivning till cache, 1 tim</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot reserverar ett uppskattat belopp före en begäran. Efter resultatet slutregleras avgiften utifrån uppmätt förbrukning. Slutreglering för strömning använder den slutliga förbrukningsposten. <a href=\"/docs/sv/billing/reserve/\">Så fungerar reservation och slutreglering →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Exempelbegäranden</h3><h4>Ailoot Ultra · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kodvarianter\"><button class=\"cg-tab\" id=\"model-code-1247-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1247-panel-0\" aria-selected=\"true\" tabindex=\"0\">Komplett minimal JSON-kropp</button><button class=\"cg-tab\" id=\"model-code-1247-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1247-panel-1\" aria-selected=\"false\" tabindex=\"-1\">curl · använd ditt UTF-8-dokument</button><button class=\"cg-tab\" id=\"model-code-1247-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1247-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python · spara hela resultatet</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiera kod\"><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-1247-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-1247-tab-0\"><pre data-lang=\"json\"><code>{\n  &quot;model&quot;: &quot;deepseek/deepseek-v3.1-terminus&quot;,\n  &quot;max_tokens&quot;: 128,\n  &quot;messages&quot;: [\n    {\n      &quot;role&quot;: &quot;user&quot;,\n      &quot;content&quot;: &quot;Summarize the incident report.&quot;\n    }\n  ],\n  &quot;stream&quot;: false\n}</code></pre></div><div class=\"cg-pane\" id=\"model-code-1247-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-1247-tab-1\" hidden><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 document}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;deepseek/deepseek-v3.1-terminus&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nPath(&#39;request.json&#39;).write_text(json.dumps(payload, ensure_ascii=False), encoding=&#39;utf-8&#39;)\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\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-1247-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-1247-tab-2\" hidden><pre data-lang=\"python\"><code>import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;deepseek/deepseek-v3.1-terminus&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ[&#39;AILOOT_API_KEY&#39;]\nif not api_key.strip():\n    raise SystemExit(&#39;Set AILOOT_API_KEY before making a request&#39;)\nheaders = {&#39;x-api-key&#39;: &#39;PLACEHOLDER_KEY&#39;, &#39;anthropic-version&#39;: &#39;2023-06-01&#39;, &#39;Content-Type&#39;: &#39;application/json&#39;}\nheaders[&#39;x-api-key&#39;] = api_key\nrequest = Request(&#39;https://api.ailoot.ai/v1/messages&#39;, data=json.dumps(payload, ensure_ascii=False).encode(&#39;utf-8&#39;), headers=headers, method=&#39;POST&#39;)\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path(&#39;response-headers.txt&#39;).write_text(str(response.headers), encoding=&#39;utf-8&#39;)\nexcept HTTPError as error:\n    Path(&#39;result.json&#39;).write_bytes(error.read())\n    Path(&#39;response-headers.txt&#39;).write_text(str(error.headers), encoding=&#39;utf-8&#39;)\n    raise\nPath(&#39;result.json&#39;).write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Ta emot och spara resultat</h3><h4>Ailoot Ultra · Anthropic Messages</h4><p class=\"note-s\">JSON eller SSE</p><div class=\"card-result-process\" data-all-results><h5>Behåll alla färdiga resultat</h5><p class=\"note-s\">Behåll varje fullständigt returnerat svar, fil och innehållsdel.</p><p class=\"note-s\">Behåll alla innehållsblock, resonemangssignaturer och faktiska ID:n för verktygsanvändning. Sätt samman alla SSE-deltauppdateringar för blocken; ett första textblock är inte hela utdata.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Om det ursprungliga svaret behöver kontrolleras</h5><p class=\"note-s\">Behåll begärans/svarets ID:n och huvuden. Ingen generell URL för hämtning av textjobb tillhandahålls.</p></div><details class=\"card-about\" data-output-fields><summary>Svarsfält</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Fält</th><th>Typ</th></tr></thead><tbody><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>string</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>string</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>string|null</td></tr><tr><th data-cell-label=\"Fält\" scope=\"row\"><span class=\"card-cell-label\">Fält</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Typ\" data-field-type><span class=\"card-cell-label\">Typ</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Fel och nästa steg</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Svar</th><th>Villkor</th><th>Nästa steg</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=\"Villkor\"><span class=\"card-cell-label\">Villkor</span>Ogiltiga obligatoriska fält, ogiltig representation av underlaget eller ogiltigt parametervärde</td><td data-cell-label=\"Nästa steg\"><span class=\"card-cell-label\">Nästa steg</span>Korrigera de angivna fälten före en ny begäran om att skapa.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Alias</h3><h4>Modellalias</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=deepseek%2Fdeepseek-v3.1-terminus&amp;route=Ultra&amp;caller=deepseek%2Fdeepseek-v3.1-terminus&amp;fmt=messages\"><code>deepseek/deepseek-v3.1-terminus</code></a></span></p><h4>Alias för metodsökvägar</h4><p class=\"note-s\">Använd metodsökvägarna som visas ovan.</p><h4>Relaterade anropar-ID:n</h4><p class=\"note-s\"><a href=\"#m=deepseek%2Fdeepseek-v3.1-terminus&amp;route=Ultra&amp;caller=deepseek%2Fdeepseek-v3.1-terminus&amp;fmt=messages\"><code>deepseek/deepseek-v3.1-terminus</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "deepseek/deepseek-v3.1-terminus",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|messages|/v1/messages|deepseek%2Fdeepseek-v3.1-terminus",
      "ordinal": 1,
      "rawMethod": {
        "available": null,
        "cache_read": 0,
        "cache_write": 0,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ogiltiga obligatoriska fält, ogiltig representation av underlaget eller ogiltigt parametervärde",
                "http_status": 400,
                "recovery": "Korrigera de angivna fälten före en ny begäran om att skapa.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "deepseek/deepseek-v3.1-terminus",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Behåll begärans/svarets ID:n och huvuden. Ingen generell URL för hämtning av textjobb tillhandahålls."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "sträng i messages[].content",
                "required_material": "UTF-8-text"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "Behåll alla innehållsblock, resonemangssignaturer och faktiska ID:n för verktygsanvändning. Sätt samman alla SSE-deltauppdateringar för blocken; ett första textblock är inte hela utdata.",
              "family": "protocol",
              "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": [
                  "deepseek/deepseek-v3.1-terminus"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "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"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "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"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "deepseek/deepseek-v3.1-terminus"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "deepseek/deepseek-v3.1-terminus",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "Läs det faktiska UTF-8-dokumentet och placera texten i det angivna input-fältet eller i strängen för meddelandets innehåll."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "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.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Grundpriser för token",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"deepseek/deepseek-v3.1-terminus\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'deepseek/deepseek-v3.1-terminus', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\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\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'deepseek/deepseek-v3.1-terminus', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "in": 1.144,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 3.43,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    }
  ],
  "model_id": "deepseek/deepseek-v3.1-terminus",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "2f90a2ceccf40cfa9ea802afaa6c460b572e6fa2c41319738574bc7870895154",
    "input_html_sha256": "bd40a1034017bdb667c001774a35ad28c75f7e566a591cf6beefb6f972a62702",
    "private_audit_sha256": "21f5d2c0d0c5e8a6834b657d4777202f61168edffcd7510b7ea77fdaae1f8a5c",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/sv/deepseek-deepseek-v3-1-terminus/",
    "description": "DeepSeek V3.1 Terminus förfinar V3.1-textmodellens språkliga konsekvens och beteendet hos kod- och sökagenter. Den behåller hybridprofilen med tänkande och direkta svar, med en kontext på 128K och en uppdaterad sökagentmall som hålls åtskild från senare V3.2-format.",
    "locale": "sv",
    "md_url": "https://ailoot.ai/models/sv/deepseek-deepseek-v3-1-terminus/index.md",
    "title": "DeepSeek: DeepSeek V3.1 Terminus — Ailoot",
    "url": "https://ailoot.ai/models/sv/deepseek-deepseek-v3-1-terminus/"
  },
  "practicalHtml": "<h3>Praktisk uppgift</h3><p>Tekniskt exempel på engelska</p><pre><code>Explain a field rule in English\n\nWrite an English explanation of this validation rule for an integration guide: &quot;retry_count must be a nonnegative integer; retry_after_ms may be omitted; when present, it must be a positive integer.&quot; Preserve the field names exactly. Add one valid and one invalid example as plain text, explaining the invalid field without translating identifiers.</code></pre><h4>Förväntat resultat</h4><pre><code>An English paragraph plus two labelled examples and a specific validation explanation.</code></pre><h4>Kontrollera resultatet</h4><pre><code>Check that retry_count accepts zero while retry_after_ms does not.</code></pre>",
  "practicalText": "Praktisk uppgift Tekniskt exempel på engelska Explain a field rule in English Write an English explanation of this validation rule for an integration guide: \"retry_count must be a nonnegative integer; retry_after_ms may be omitted; when present, it must be a positive integer.\" Preserve the field names exactly. Add one valid and one invalid example as plain text, explaining the invalid field without translating identifiers. Förväntat resultat An English paragraph plus two labelled examples and a specific validation explanation. Kontrollera resultatet Check that retry_count accepts zero while retry_after_ms does not.",
  "rawModel": {
    "about": "DeepSeek V3.1 Terminus är DeepSeeks uppdatering av textmodellprofilen V3.1. Den behåller de ursprungliga förmågorna och hanterar samtidigt oönskad blandning av kinesiska och engelska, enstaka avvikande tecken och beteendet hos kod- och sökagenter. Indata är en skriftlig uppgift och källkontext; utdata är text, som kan innehålla en förklaring, föreslagen kod eller agentrelaterat innehåll. Den namngivna Terminus-utgåvan förblir separat från ursprungliga V3.1 och senare utgåvor med gles attention.\n\nDen ärvda V3.1-profilen är hybrid: en modell kan svara i läge med eller utan tänkande genom sin chattmall. V3.1:s publicerade modelltabell anger totalt 671 miljarder parametrar, 37 miljarder aktiva parametrar och en kontext på 128K. Terminus beskriver samma modellstruktur som V3 och hänvisar till V3.1 för konversationsmallen utanför det reviderade arbetsflödet för sökagenten. Dessa referenser kopplar uppdateringen till den underliggande familjen och bevarar samtidigt dess egna ändringar.\n\nFör en direkt kodningsassistent stöder den ärvda mallen standardverktygsanrop i läget utan tänkande, med namngivna funktioner och JSON-argument baserade på de tillhandahållna verktygsdefinitionerna. Modellen föreslår operationen, applikationen utför den och returnerar observationen. Sökning i tänkandeläge följer ett specialiserat sökagentformat. Terminus uppdaterar sökmallen och verktygsuppsättningen, så sökförloppet ska använda Terminus-referensen snarare än en orelaterad mall från en annan utgåva.\n\nSpråklig konsekvens är en praktisk skillnad mellan utgåvorna. För en dokumentuppgift på kinesiska eller engelska anger du svarsspråket, termerna som måste behålla sin ursprungliga stavning och källavsnitten som ska användas. Ett exempel på uppdragsbeskrivning är: ”Skriv förklaringen på engelska, bevara de tillhandahållna variabelnamnen och undvik att översätta API-fältnamnen. Basera varje iakttagelse på den tillhandahållna specifikationen.” Uppdateringen riktar in sig på oönskad språkväxling, medan din uppdragsbeskrivning fortfarande definierar vilket flerspråkigt material som är avsiktligt.\n\nModellen kan använda ett användartillhandahållet sökverktyg för frågor som kräver extern eller aktuell information. Tillhandahåll researchfrågan, kriterierna för användbara källor och slutleveransen. En kodningsuppgift ska innehålla det relevanta fragmentet, observerat beteende och förväntat resultat. Håll verktygsreturer kopplade till den operation som skapade dem och be slutsvaret identifiera beläggen bakom en föreslagen ändring eller slutsats.\n\nProducenten registrerar en checkpointspecifik precisionsdetalj: parametrarna för attention-utdataprojektionen följer inte skalformatet UE8M0 FP8 som används i V3.1-utgåvan. Det är en aspekt av referensimplementationen, inte en ändring av uppgiftens språk, modalitet eller svarsformat. Det är ett skäl att behålla Terminus som en egen utgåva och undvika att behandla alla V3.1-checkpoints som identiska precisionsprofiler.\n\nFör längre arbete budgeterar du källmaterialet, konversationen och det genererade svaret inom familjekontexten på 128K. Märk dokumentavsnitt och kodfragment så att ett resultat kan hänvisa tillbaka till rätt belägg. I en uppgift med flera steg definierar du de tillåtna åtgärderna, den obligatoriska leveransen och färdigställandekriteriet. Det användbara resultatet är ett konsekvent textsvar, kodförslag eller en källstödd analys som kan granskas mot indata och de faktiska verktygsobservationerna.",
    "alias_of": null,
    "aliases": [],
    "author": "DeepSeek",
    "available": null,
    "canonical_model": "deepseek/deepseek-v3.1-terminus",
    "capabilities": {
      "context_length": 163840,
      "manufacturer_input": [
        "text"
      ],
      "manufacturer_output": [
        "text"
      ]
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          }
        ],
        "summary": "Fullständig prissättning för konfigurationen finns i detaljerna."
      }
    ],
    "ctx": null,
    "entity_type": "model",
    "formats": [
      "chat",
      "messages"
    ],
    "id": "deepseek/deepseek-v3.1-terminus",
    "input": [
      "text"
    ],
    "kind": "text",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": 0,
        "cache_write": 0,
        "cache_write_1h": 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": "Ogiltiga obligatoriska fält, ogiltig representation av underlaget eller ogiltigt parametervärde",
                "http_status": 400,
                "recovery": "Korrigera de angivna fälten före en ny begäran om att skapa.",
                "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.",
              "Guarded canonical keys must occur once; duplicate or case-varied model/tools/cap fields are rejected."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Behåll begärans/svarets ID:n och huvuden. Ingen generell URL för hämtning av textjobb tillhandahålls."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8-text"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "Behåll varje svarsalternativ och dess innehåll/verktygsanrop/resonemang. Sätt i SSE samman deltauppdateringar efter svarsalternativets/verktygets index och behåll den slutliga avslutsorsaken och användningsuppgifterna.",
              "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": [
                  "deepseek/deepseek-v3.1-terminus"
                ],
                "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": "Dessa roller representeras uttryckligen av källkodens kompatibilitetstyper; den exakta rolluppsättningen är fortfarande modellspecifik.",
                "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; använd det faktiska returnerade ID:t"
              },
              {
                "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": "Skicka tillbaka det faktiska returnerade resonemanget när modellen använder 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": [
                  "function"
                ],
                "enum_known": true,
                "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": "verktyg av typen funktion har tillhandahållits"
              },
              {
                "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"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "text"
                ],
                "enum_known": true,
                "name": "modalities",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "conditions": "provider.options avvisas på denna Ultra-textrutt",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "conditions": "1h avvisas på de faktiska platserna för promptcache",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control.ttl",
                "required": false,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "Skicka det exakta modell-ID:t tillsammans med messages.",
            "Kontextlängden är inte en utdatagräns.",
            "En textfil kan tillhandahålla bokstavlig text; bild-/ljud-/filobjektsindata kräver exakt bindning."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "modellspecifikt; användarens funktionsverktyg skiljer sig från värdbaserade verktyg",
            "file_material": "det faktiska UTF-8-dokumentet infogat som bokstavlig text; inget fil-ID härleds",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "meddelandearray med strukturen role/content",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream",
              "temperature",
              "top_p",
              "stop",
              "max_tokens",
              "max_completion_tokens",
              "reasoning",
              "response_format",
              "tools",
              "tool_choice"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Grundpriser för token",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"deepseek/deepseek-v3.1-terminus\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}]}')\n\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\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "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)\nresult=client.chat.completions.create(model='deepseek/deepseek-v3.1-terminus',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}])\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(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          },
          {
            "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='deepseek/deepseek-v3.1-terminus',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 SDK streaming · all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 1.144,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 3.43,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "available": null,
        "cache_read": 0,
        "cache_write": 0,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "Ogiltiga obligatoriska fält, ogiltig representation av underlaget eller ogiltigt parametervärde",
                "http_status": 400,
                "recovery": "Korrigera de angivna fälten före en ny begäran om att skapa.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "deepseek/deepseek-v3.1-terminus",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "Behåll begärans/svarets ID:n och huvuden. Ingen generell URL för hämtning av textjobb tillhandahålls."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "sträng i messages[].content",
                "required_material": "UTF-8-text"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "Behåll alla innehållsblock, resonemangssignaturer och faktiska ID:n för verktygsanvändning. Sätt samman alla SSE-deltauppdateringar för blocken; ett första textblock är inte hela utdata.",
              "family": "protocol",
              "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": [
                  "deepseek/deepseek-v3.1-terminus"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "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"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "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"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "deepseek/deepseek-v3.1-terminus"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "deepseek/deepseek-v3.1-terminus",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "Läs det faktiska UTF-8-dokumentet och placera texten i det angivna input-fältet eller i strängen för meddelandets innehåll."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "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.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Grundpriser för token",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"deepseek/deepseek-v3.1-terminus\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'deepseek/deepseek-v3.1-terminus', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\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\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'deepseek/deepseek-v3.1-terminus', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "in": 1.144,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 3.43,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.001144000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.000001144",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.00343000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.00000343",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "deepseek/deepseek-v3.1-terminus",
        "request_model_id": "deepseek/deepseek-v3.1-terminus",
        "route_label": "Ultra"
      }
    ],
    "name": "DeepSeek: DeepSeek V3.1 Terminus",
    "price": {
      "in": 1.144,
      "in_label": null,
      "out": 3.43,
      "out_label": null,
      "scope_label": "Token rates",
      "sort_in": 1.144,
      "sort_out": 3.43,
      "varies": false
    },
    "pricing_profiles": [
      {
        "dimensions": {
          "regime": "base"
        },
        "label": "OpenAI Chat · Base token rates",
        "units": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "dimensions": {
          "regime": "base"
        },
        "label": "Anthropic Messages · Base token rates",
        "units": [
          {
            "amount": "0.001144000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.000001144",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.00343000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.00000343",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    ],
    "public_id": "deepseek/deepseek-v3.1-terminus",
    "short": "DeepSeek V3.1 Terminus förfinar V3.1-textmodellens språkliga konsekvens och beteendet hos kod- och sökagenter. Den behåller hybridprofilen med tänkande och direkta svar, med en kontext på 128K och en uppdaterad sökagentmall som hålls åtskild från senare V3.2-format."
  },
  "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
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod",
        "/methods/1/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "DeepSeek V3.1 Terminus förfinar V3.1-textmodellens språkliga konsekvens och beteendet hos kod- och sökagenter. Den behåller hybridprofilen med tänkande och direkta svar, med en kontext på 128K och en uppdaterad sökagentmall som hålls åtskild från senare V3.2-format.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "6670d380599d9e3c99b1bdb57079c031d0e6ba81b01d946c8f66112f20bcfc69",
    "renderer_sha256": "8a45bb31b83d2551e6d975cf4683518c7cb445a54b9394a01947f4dd103f1051"
  },
  "sourceRevision": "6e36aa64ae5b5a2e4af2fd1e34576ad9843e002d85c01e2c8ea539172fb3ed3d"
}