{
  "aboutHtml": "<p>Inledning: den instruktionsanpassade 3B-utgåvan</p><p>Qwen2.5-VL-3B-Instruct är 3B-medlemmen i Qwen2.5-VL. Den tar emot textinstruktioner med bilder eller video och genererar textsvar, inklusive strukturerade data. Välj den för en tydligt definierad visuell fråga, en dokumentextraktionsuppgift eller en förklaring som kopplar synligt innehåll till användarens begäran. Exakt denna storlek och utgåva behåller sin egen identitet; funktioner som lagts till särskilt för andra storlekar eller senare Qwen-generationer bör inte antas gälla denna kontrollpunkt.</p><p>Visuell förståelse och agentflöden</p><p>Qwen beskriver igenkänning av vanliga objekt och analys av skrift, diagram, ikoner, grafik och sidlayout. För ett formulär ska nödvändiga fält och betydelsen av ett tomt värde anges. För ett diagram ska axlar, enheter och synliga värden som stöder slutsatsen efterfrågas. En fokuserad begäran gör resultatet lättare att jämföra med originalbilden än en bred begäran att beskriva allt.</p><p>Familjen stöder också resonemang som visuell agent och styrning av verktyg för dator- eller telefonflöden. Modellen kan tolka ett gränssnitt och bidra till ett åtgärdsbeslut; anslutna applikationsverktyg utför åtgärden. En skärmbildsgranskning kan fråga vilken kontroll som motsvarar en uppgift och vilken synlig information som stöder valet. Den användningen av visuellt resonemang ger inte i sig kontroll över en enhet.</p><p>Lång video och händelselokalisering</p><p>Tillverkaren beskriver förståelse av videor längre än en timme och identifiering av segment som är relevanta för en begärd händelse. Det är en familjeförmåga, inte en ovillkorlig gräns för medieuppladdning eller en garanti att varje bildruta behålls. Förbered det relevanta klippet, bevara tidsinformationen och ställ en precis fråga om händelsen, sekvensen eller förändringen. Modellens videobearbetning använder bildfrekvensinformation för att anpassa visuella observationer till absolut tid.</p><p>Lokalisering och strukturerade dokument</p><p>Qwen2.5-VL kan returnera objektplatser som begränsningsrutor eller punkter, med koordinater och attribut i JSON. För en lokaliseringsuppgift ska målobjektet namnges och det anges om resultatet ska vara en punkt eller en ruta. Håll koordinatkonventionen uttrycklig i den konsumerande applikationen i stället för att härleda ett fysiskt mått ur ett godtyckligt fotografi.</p><p>Tillverkaren dokumenterar även strukturerad extraktion från skannade fakturor, formulär och tabeller. Tillhandahåll en läsbar sida och ett utdataschema: exempelvis fältnamn, extraherad text och det synliga område som stöder den. Bevara enheter, decimaltecken och tabellrubriker i källan. Behandla osäkert eller oläsligt innehåll som ett granskningsfall i stället för att be modellen hitta på ett saknat värde. Dessa förberedelseexempel tillämpar dokumenterade förmågor; de är inga garantier för exakt extraktion.</p><p>Arkitekturändringar</p><p>Dynamisk bildupplösning utvidgas till video genom träning med varierande bildfrekvens. Uppdaterad multimodal positionskodning representerar tidssekvens och absolut tid och hjälper till att identifiera specifika ögonblick och hastighetsförändringar. Bildkodaren använder window attention tillsammans med SwiGLU och RMSNorm. Ändringarna beskriver hur modellen bearbetar visuellt material; de fastställer ingen bestämd latens för en viss applikation.</p><p>Förbereda bilder och video</p><p>De officiella exemplen omfattar enskilda bilder, flera bilder, rena textsamtal, videofiler och ordnade listor med bildrutor. Märk flera visuella indata så att en fråga kan hänvisa till var och en. För en bildjämförelse ska en tabell organiserad efter etiketterna begäras och resultatet begränsas till synliga skillnader. För en videotidslinje ska bildrutornas ordning och timing bevaras i stället för att fristående bilder presenteras som om de hade en känd varaktighet.</p><p>Bildprocessorns dokumenterade standardintervall går från fyra till 16,384 visuella token per bild. Exemplet kan sikta på 256–1,280 token genom att sätta pixelgränser. Det bevarar bildförhållandet inom gränserna, medan uttryckliga ändrade mått anpassas till multiplar av 28. Fler detaljer kräver mer beräkning och sekvensutrymme, så ett litet textfält kan behöva ett utsnitt med högre upplösning medan en bred scenbeskrivning kanske inte gör det. Detta är tillverkarens bearbetningskontroller; applikationens uppladdningsalternativ kan skilja sig.</p><p>Kontext och väsentliga begränsningar</p><p>Den publicerade kontrollpunktskonfigurationen anger högsta antal positioner till 128,000, medan det medföljande avsnittet om lång text fortfarande diskuterar en startkonfiguration på 32,768 token. Guiden beskriver YaRN-extrapolering men varnar för att den kan påverka temporal och spatial lokalisering avsevärt och rekommenderar inte metoden för dessa uppgifter. Den nämner separat att positionskodning för video kan tillåta en större positionsinställning, med 64K som exempel. Dessa olika konfigurationsbeskrivningar bör inte sammanföras till ett enda universellt validerat indatatak.</p><p>Text, visuellt material och svar delar en ändlig sekvensbudget. Håll relevant innehåll läsligt, reservera plats för resultatet och kontrollera extraherad text, koordinater och händelsetider mot originalet. Modellkortets genereringsexempel med 128 token är illustrativt och fastställer ingen separat hård utdatagräns. Modellen returnerar textanalys eller strukturerad information; dess förmågor för bild och språk innebär inte att den genererar bilder eller video.</p>",
  "aboutText": "Inledning: den instruktionsanpassade 3B-utgåvan\n\nQwen2.5-VL-3B-Instruct är 3B-medlemmen i Qwen2.5-VL. Den tar emot textinstruktioner med bilder eller video och genererar textsvar, inklusive strukturerade data. Välj den för en tydligt definierad visuell fråga, en dokumentextraktionsuppgift eller en förklaring som kopplar synligt innehåll till användarens begäran. Exakt denna storlek och utgåva behåller sin egen identitet; funktioner som lagts till särskilt för andra storlekar eller senare Qwen-generationer bör inte antas gälla denna kontrollpunkt.\n\nVisuell förståelse och agentflöden\n\nQwen beskriver igenkänning av vanliga objekt och analys av skrift, diagram, ikoner, grafik och sidlayout. För ett formulär ska nödvändiga fält och betydelsen av ett tomt värde anges. För ett diagram ska axlar, enheter och synliga värden som stöder slutsatsen efterfrågas. En fokuserad begäran gör resultatet lättare att jämföra med originalbilden än en bred begäran att beskriva allt.\n\nFamiljen stöder också resonemang som visuell agent och styrning av verktyg för dator- eller telefonflöden. Modellen kan tolka ett gränssnitt och bidra till ett åtgärdsbeslut; anslutna applikationsverktyg utför åtgärden. En skärmbildsgranskning kan fråga vilken kontroll som motsvarar en uppgift och vilken synlig information som stöder valet. Den användningen av visuellt resonemang ger inte i sig kontroll över en enhet.\n\nLång video och händelselokalisering\n\nTillverkaren beskriver förståelse av videor längre än en timme och identifiering av segment som är relevanta för en begärd händelse. Det är en familjeförmåga, inte en ovillkorlig gräns för medieuppladdning eller en garanti att varje bildruta behålls. Förbered det relevanta klippet, bevara tidsinformationen och ställ en precis fråga om händelsen, sekvensen eller förändringen. Modellens videobearbetning använder bildfrekvensinformation för att anpassa visuella observationer till absolut tid.\n\nLokalisering och strukturerade dokument\n\nQwen2.5-VL kan returnera objektplatser som begränsningsrutor eller punkter, med koordinater och attribut i JSON. För en lokaliseringsuppgift ska målobjektet namnges och det anges om resultatet ska vara en punkt eller en ruta. Håll koordinatkonventionen uttrycklig i den konsumerande applikationen i stället för att härleda ett fysiskt mått ur ett godtyckligt fotografi.\n\nTillverkaren dokumenterar även strukturerad extraktion från skannade fakturor, formulär och tabeller. Tillhandahåll en läsbar sida och ett utdataschema: exempelvis fältnamn, extraherad text och det synliga område som stöder den. Bevara enheter, decimaltecken och tabellrubriker i källan. Behandla osäkert eller oläsligt innehåll som ett granskningsfall i stället för att be modellen hitta på ett saknat värde. Dessa förberedelseexempel tillämpar dokumenterade förmågor; de är inga garantier för exakt extraktion.\n\nArkitekturändringar\n\nDynamisk bildupplösning utvidgas till video genom träning med varierande bildfrekvens. Uppdaterad multimodal positionskodning representerar tidssekvens och absolut tid och hjälper till att identifiera specifika ögonblick och hastighetsförändringar. Bildkodaren använder window attention tillsammans med SwiGLU och RMSNorm. Ändringarna beskriver hur modellen bearbetar visuellt material; de fastställer ingen bestämd latens för en viss applikation.\n\nFörbereda bilder och video\n\nDe officiella exemplen omfattar enskilda bilder, flera bilder, rena textsamtal, videofiler och ordnade listor med bildrutor. Märk flera visuella indata så att en fråga kan hänvisa till var och en. För en bildjämförelse ska en tabell organiserad efter etiketterna begäras och resultatet begränsas till synliga skillnader. För en videotidslinje ska bildrutornas ordning och timing bevaras i stället för att fristående bilder presenteras som om de hade en känd varaktighet.\n\nBildprocessorns dokumenterade standardintervall går från fyra till 16,384 visuella token per bild. Exemplet kan sikta på 256–1,280 token genom att sätta pixelgränser. Det bevarar bildförhållandet inom gränserna, medan uttryckliga ändrade mått anpassas till multiplar av 28. Fler detaljer kräver mer beräkning och sekvensutrymme, så ett litet textfält kan behöva ett utsnitt med högre upplösning medan en bred scenbeskrivning kanske inte gör det. Detta är tillverkarens bearbetningskontroller; applikationens uppladdningsalternativ kan skilja sig.\n\nKontext och väsentliga begränsningar\n\nDen publicerade kontrollpunktskonfigurationen anger högsta antal positioner till 128,000, medan det medföljande avsnittet om lång text fortfarande diskuterar en startkonfiguration på 32,768 token. Guiden beskriver YaRN-extrapolering men varnar för att den kan påverka temporal och spatial lokalisering avsevärt och rekommenderar inte metoden för dessa uppgifter. Den nämner separat att positionskodning för video kan tillåta en större positionsinställning, med 64K som exempel. Dessa olika konfigurationsbeskrivningar bör inte sammanföras till ett enda universellt validerat indatatak.\n\nText, visuellt material och svar delar en ändlig sekvensbudget. Håll relevant innehåll läsligt, reservera plats för resultatet och kontrollera extraherad text, koordinater och händelsetider mot originalet. Modellkortets genereringsexempel med 128 token är illustrativt och fastställer ingen separat hård utdatagräns. Modellen returnerar textanalys eller strukturerad information; dess förmågor för bild och språk innebär inte att den genererar bilder eller video.",
  "editorialOverlay": {
    "copy_fields": {
      "practical_html": "<h3>Praktisk uppgift</h3><p>Tekniskt exempel på engelska</p><pre><code>Organize a recorded event timeline\n\nUse only these text annotations from a clip: 00:02 worker picks up a box; 00:05 worker places the box on the scale; 00:08 scale display is obscured; 00:11 worker removes the box. Return the event sequence, the first annotated placement time and whether the weight is established. Preserve timestamps without claiming frame-level inspection.</code></pre><h4>Förväntat resultat</h4><pre><code>An ordered event table, a placement-time field and an unresolved weight field.</code></pre><h4>Kontrollera resultatet</h4><pre><code>Check that obscured weight remains unknown and the placement timestamp is attributed to the supplied annotation.</code></pre>"
    },
    "copy_sha256": "c225a9fb3ea1c41cccc7a42a794bbdc446fe58764c1c176e7786cabbf3bf4918",
    "copy_source": {
      "locale": "sv",
      "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7",
      "record_model_id": "qwen2.5-vl-3b-instruct",
      "source_facts_sha256": "9946afce1723b829ed6112a3e5ab5186a0e0525e4e0cee399ff5b525def302c0",
      "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6"
    },
    "html_sha256": "a47837e0c1e4186705a478a206898d79e9e6c68a918b0c08a7af2ccb15d8944d",
    "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\">Al</span><h2 id=\"sheet-title\">Qwen2.5-VL-3b</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Stäng\">×</button></div><div class=\"idline\"><span>Alibaba /</span><code>qwen2.5-vl-3b-instruct</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|qwen2.5-vl-3b-instruct\">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|qwen2.5-vl-3b-instruct\">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\">Qwen2.5-VL-3B-Instruct är Qwens kompakta instruktionsanpassade modell för bild och språk, avsedd för text, bilder och video. Den returnerar text och strukturerad visuell information, inklusive dokumentfält, objektkoordinater och händelsebeskrivningar, med dynamisk upplösning och tidsmedveten videobearbetning.</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>Inledning: den instruktionsanpassade 3B-utgåvan</p><p>Qwen2.5-VL-3B-Instruct är 3B-medlemmen i Qwen2.5-VL. Den tar emot textinstruktioner med bilder eller video och genererar textsvar, inklusive strukturerade data. Välj den för en tydligt definierad visuell fråga, en dokumentextraktionsuppgift eller en förklaring som kopplar synligt innehåll till användarens begäran. Exakt denna storlek och utgåva behåller sin egen identitet; funktioner som lagts till särskilt för andra storlekar eller senare Qwen-generationer bör inte antas gälla denna kontrollpunkt.</p><p>Visuell förståelse och agentflöden</p><p>Qwen beskriver igenkänning av vanliga objekt och analys av skrift, diagram, ikoner, grafik och sidlayout. För ett formulär ska nödvändiga fält och betydelsen av ett tomt värde anges. För ett diagram ska axlar, enheter och synliga värden som stöder slutsatsen efterfrågas. En fokuserad begäran gör resultatet lättare att jämföra med originalbilden än en bred begäran att beskriva allt.</p><p>Familjen stöder också resonemang som visuell agent och styrning av verktyg för dator- eller telefonflöden. Modellen kan tolka ett gränssnitt och bidra till ett åtgärdsbeslut; anslutna applikationsverktyg utför åtgärden. En skärmbildsgranskning kan fråga vilken kontroll som motsvarar en uppgift och vilken synlig information som stöder valet. Den användningen av visuellt resonemang ger inte i sig kontroll över en enhet.</p><p>Lång video och händelselokalisering</p><p>Tillverkaren beskriver förståelse av videor längre än en timme och identifiering av segment som är relevanta för en begärd händelse. Det är en familjeförmåga, inte en ovillkorlig gräns för medieuppladdning eller en garanti att varje bildruta behålls. Förbered det relevanta klippet, bevara tidsinformationen och ställ en precis fråga om händelsen, sekvensen eller förändringen. Modellens videobearbetning använder bildfrekvensinformation för att anpassa visuella observationer till absolut tid.</p><p>Lokalisering och strukturerade dokument</p><p>Qwen2.5-VL kan returnera objektplatser som begränsningsrutor eller punkter, med koordinater och attribut i JSON. För en lokaliseringsuppgift ska målobjektet namnges och det anges om resultatet ska vara en punkt eller en ruta. Håll koordinatkonventionen uttrycklig i den konsumerande applikationen i stället för att härleda ett fysiskt mått ur ett godtyckligt fotografi.</p><p>Tillverkaren dokumenterar även strukturerad extraktion från skannade fakturor, formulär och tabeller. Tillhandahåll en läsbar sida och ett utdataschema: exempelvis fältnamn, extraherad text och det synliga område som stöder den. Bevara enheter, decimaltecken och tabellrubriker i källan. Behandla osäkert eller oläsligt innehåll som ett granskningsfall i stället för att be modellen hitta på ett saknat värde. Dessa förberedelseexempel tillämpar dokumenterade förmågor; de är inga garantier för exakt extraktion.</p><p>Arkitekturändringar</p><p>Dynamisk bildupplösning utvidgas till video genom träning med varierande bildfrekvens. Uppdaterad multimodal positionskodning representerar tidssekvens och absolut tid och hjälper till att identifiera specifika ögonblick och hastighetsförändringar. Bildkodaren använder window attention tillsammans med SwiGLU och RMSNorm. Ändringarna beskriver hur modellen bearbetar visuellt material; de fastställer ingen bestämd latens för en viss applikation.</p><p>Förbereda bilder och video</p><p>De officiella exemplen omfattar enskilda bilder, flera bilder, rena textsamtal, videofiler och ordnade listor med bildrutor. Märk flera visuella indata så att en fråga kan hänvisa till var och en. För en bildjämförelse ska en tabell organiserad efter etiketterna begäras och resultatet begränsas till synliga skillnader. För en videotidslinje ska bildrutornas ordning och timing bevaras i stället för att fristående bilder presenteras som om de hade en känd varaktighet.</p><p>Bildprocessorns dokumenterade standardintervall går från fyra till 16,384 visuella token per bild. Exemplet kan sikta på 256–1,280 token genom att sätta pixelgränser. Det bevarar bildförhållandet inom gränserna, medan uttryckliga ändrade mått anpassas till multiplar av 28. Fler detaljer kräver mer beräkning och sekvensutrymme, så ett litet textfält kan behöva ett utsnitt med högre upplösning medan en bred scenbeskrivning kanske inte gör det. Detta är tillverkarens bearbetningskontroller; applikationens uppladdningsalternativ kan skilja sig.</p><p>Kontext och väsentliga begränsningar</p><p>Den publicerade kontrollpunktskonfigurationen anger högsta antal positioner till 128,000, medan det medföljande avsnittet om lång text fortfarande diskuterar en startkonfiguration på 32,768 token. Guiden beskriver YaRN-extrapolering men varnar för att den kan påverka temporal och spatial lokalisering avsevärt och rekommenderar inte metoden för dessa uppgifter. Den nämner separat att positionskodning för video kan tillåta en större positionsinställning, med 64K som exempel. Dessa olika konfigurationsbeskrivningar bör inte sammanföras till ett enda universellt validerat indatatak.</p><p>Text, visuellt material och svar delar en ändlig sekvensbudget. Håll relevant innehåll läsligt, reservera plats för resultatet och kontrollera extraherad text, koordinater och händelsetider mot originalet. Modellkortets genereringsexempel med 128 token är illustrativt och fastställer ingen separat hård utdatagräns. Modellen returnerar textanalys eller strukturerad information; dess förmågor för bild och språk innebär inte att den genererar bilder eller video.</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>qwen2.5-vl-3b-instruct</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>$0.0004</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Utdata · Utdatatoken</span> <b>$0.0012</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-2480-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2480-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-2480-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2480-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-2480-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2480-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-2480-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-2480-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;qwen2.5-vl-3b-instruct&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-2480-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-2480-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;qwen2.5-vl-3b-instruct&#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-2480-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-2480-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;qwen2.5-vl-3b-instruct&#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=qwen2.5-vl-3b-instruct&amp;route=Ultra&amp;caller=qwen2.5-vl-3b-instruct&amp;fmt=chat\"><code>qwen2.5-vl-3b-instruct</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=qwen2.5-vl-3b-instruct&amp;route=Ultra&amp;caller=qwen2.5-vl-3b-instruct&amp;fmt=chat\"><code>qwen2.5-vl-3b-instruct</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "qwen2.5-vl-3b-instruct",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|chat|/v1/chat/completions|qwen2.5-vl-3b-instruct",
      "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": [
                  "qwen2.5-vl-3b-instruct"
                ],
                "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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\": \"qwen2.5-vl-3b-instruct\", \"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='qwen2.5-vl-3b-instruct',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='qwen2.5-vl-3b-instruct',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": 0.4,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 1.2,
        "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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\">Al</span><h2 id=\"sheet-title\">Qwen2.5-VL-3b</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Stäng\">×</button></div><div class=\"idline\"><span>Alibaba /</span><code>qwen2.5-vl-3b-instruct</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|qwen2.5-vl-3b-instruct\">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|qwen2.5-vl-3b-instruct\">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\">Qwen2.5-VL-3B-Instruct är Qwens kompakta instruktionsanpassade modell för bild och språk, avsedd för text, bilder och video. Den returnerar text och strukturerad visuell information, inklusive dokumentfält, objektkoordinater och händelsebeskrivningar, med dynamisk upplösning och tidsmedveten videobearbetning.</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>Inledning: den instruktionsanpassade 3B-utgåvan</p><p>Qwen2.5-VL-3B-Instruct är 3B-medlemmen i Qwen2.5-VL. Den tar emot textinstruktioner med bilder eller video och genererar textsvar, inklusive strukturerade data. Välj den för en tydligt definierad visuell fråga, en dokumentextraktionsuppgift eller en förklaring som kopplar synligt innehåll till användarens begäran. Exakt denna storlek och utgåva behåller sin egen identitet; funktioner som lagts till särskilt för andra storlekar eller senare Qwen-generationer bör inte antas gälla denna kontrollpunkt.</p><p>Visuell förståelse och agentflöden</p><p>Qwen beskriver igenkänning av vanliga objekt och analys av skrift, diagram, ikoner, grafik och sidlayout. För ett formulär ska nödvändiga fält och betydelsen av ett tomt värde anges. För ett diagram ska axlar, enheter och synliga värden som stöder slutsatsen efterfrågas. En fokuserad begäran gör resultatet lättare att jämföra med originalbilden än en bred begäran att beskriva allt.</p><p>Familjen stöder också resonemang som visuell agent och styrning av verktyg för dator- eller telefonflöden. Modellen kan tolka ett gränssnitt och bidra till ett åtgärdsbeslut; anslutna applikationsverktyg utför åtgärden. En skärmbildsgranskning kan fråga vilken kontroll som motsvarar en uppgift och vilken synlig information som stöder valet. Den användningen av visuellt resonemang ger inte i sig kontroll över en enhet.</p><p>Lång video och händelselokalisering</p><p>Tillverkaren beskriver förståelse av videor längre än en timme och identifiering av segment som är relevanta för en begärd händelse. Det är en familjeförmåga, inte en ovillkorlig gräns för medieuppladdning eller en garanti att varje bildruta behålls. Förbered det relevanta klippet, bevara tidsinformationen och ställ en precis fråga om händelsen, sekvensen eller förändringen. Modellens videobearbetning använder bildfrekvensinformation för att anpassa visuella observationer till absolut tid.</p><p>Lokalisering och strukturerade dokument</p><p>Qwen2.5-VL kan returnera objektplatser som begränsningsrutor eller punkter, med koordinater och attribut i JSON. För en lokaliseringsuppgift ska målobjektet namnges och det anges om resultatet ska vara en punkt eller en ruta. Håll koordinatkonventionen uttrycklig i den konsumerande applikationen i stället för att härleda ett fysiskt mått ur ett godtyckligt fotografi.</p><p>Tillverkaren dokumenterar även strukturerad extraktion från skannade fakturor, formulär och tabeller. Tillhandahåll en läsbar sida och ett utdataschema: exempelvis fältnamn, extraherad text och det synliga område som stöder den. Bevara enheter, decimaltecken och tabellrubriker i källan. Behandla osäkert eller oläsligt innehåll som ett granskningsfall i stället för att be modellen hitta på ett saknat värde. Dessa förberedelseexempel tillämpar dokumenterade förmågor; de är inga garantier för exakt extraktion.</p><p>Arkitekturändringar</p><p>Dynamisk bildupplösning utvidgas till video genom träning med varierande bildfrekvens. Uppdaterad multimodal positionskodning representerar tidssekvens och absolut tid och hjälper till att identifiera specifika ögonblick och hastighetsförändringar. Bildkodaren använder window attention tillsammans med SwiGLU och RMSNorm. Ändringarna beskriver hur modellen bearbetar visuellt material; de fastställer ingen bestämd latens för en viss applikation.</p><p>Förbereda bilder och video</p><p>De officiella exemplen omfattar enskilda bilder, flera bilder, rena textsamtal, videofiler och ordnade listor med bildrutor. Märk flera visuella indata så att en fråga kan hänvisa till var och en. För en bildjämförelse ska en tabell organiserad efter etiketterna begäras och resultatet begränsas till synliga skillnader. För en videotidslinje ska bildrutornas ordning och timing bevaras i stället för att fristående bilder presenteras som om de hade en känd varaktighet.</p><p>Bildprocessorns dokumenterade standardintervall går från fyra till 16,384 visuella token per bild. Exemplet kan sikta på 256–1,280 token genom att sätta pixelgränser. Det bevarar bildförhållandet inom gränserna, medan uttryckliga ändrade mått anpassas till multiplar av 28. Fler detaljer kräver mer beräkning och sekvensutrymme, så ett litet textfält kan behöva ett utsnitt med högre upplösning medan en bred scenbeskrivning kanske inte gör det. Detta är tillverkarens bearbetningskontroller; applikationens uppladdningsalternativ kan skilja sig.</p><p>Kontext och väsentliga begränsningar</p><p>Den publicerade kontrollpunktskonfigurationen anger högsta antal positioner till 128,000, medan det medföljande avsnittet om lång text fortfarande diskuterar en startkonfiguration på 32,768 token. Guiden beskriver YaRN-extrapolering men varnar för att den kan påverka temporal och spatial lokalisering avsevärt och rekommenderar inte metoden för dessa uppgifter. Den nämner separat att positionskodning för video kan tillåta en större positionsinställning, med 64K som exempel. Dessa olika konfigurationsbeskrivningar bör inte sammanföras till ett enda universellt validerat indatatak.</p><p>Text, visuellt material och svar delar en ändlig sekvensbudget. Håll relevant innehåll läsligt, reservera plats för resultatet och kontrollera extraherad text, koordinater och händelsetider mot originalet. Modellkortets genereringsexempel med 128 token är illustrativt och fastställer ingen separat hård utdatagräns. Modellen returnerar textanalys eller strukturerad information; dess förmågor för bild och språk innebär inte att den genererar bilder eller video.</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>qwen2.5-vl-3b-instruct</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>$0.0004</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Utdata · Utdatatoken</span> <b>$0.0012</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-2481-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2481-panel-0\" aria-selected=\"true\" tabindex=\"0\">Komplett minimal JSON-kropp</button><button class=\"cg-tab\" id=\"model-code-2481-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2481-panel-1\" aria-selected=\"false\" tabindex=\"-1\">curl · använd ditt UTF-8-dokument</button><button class=\"cg-tab\" id=\"model-code-2481-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2481-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-2481-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-2481-tab-0\"><pre data-lang=\"json\"><code>{\n  &quot;model&quot;: &quot;qwen2.5-vl-3b-instruct&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-2481-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-2481-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;qwen2.5-vl-3b-instruct&#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-2481-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-2481-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;qwen2.5-vl-3b-instruct&#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=qwen2.5-vl-3b-instruct&amp;route=Ultra&amp;caller=qwen2.5-vl-3b-instruct&amp;fmt=messages\"><code>qwen2.5-vl-3b-instruct</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=qwen2.5-vl-3b-instruct&amp;route=Ultra&amp;caller=qwen2.5-vl-3b-instruct&amp;fmt=messages\"><code>qwen2.5-vl-3b-instruct</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "qwen2.5-vl-3b-instruct",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|messages|/v1/messages|qwen2.5-vl-3b-instruct",
      "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": "qwen2.5-vl-3b-instruct",
              "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": [
                  "qwen2.5-vl-3b-instruct"
                ],
                "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": [
                    "qwen2.5-vl-3b-instruct"
                  ],
                  "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": "qwen2.5-vl-3b-instruct",
              "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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\": \"qwen2.5-vl-3b-instruct\",\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': 'qwen2.5-vl-3b-instruct', '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': 'qwen2.5-vl-3b-instruct', '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": 0.4,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 1.2,
        "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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": "qwen2.5-vl-3b-instruct",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "1c5b96b696c04679eed14bdd3d2a4c9680e919938e78c5df84e5ce99a919e45b",
    "input_html_sha256": "a042a35e12d6930662e8b766063b7b0a72e0fb569b3ae0d9767e3aedd3ea8d22",
    "private_audit_sha256": "3fb749125acd820439b13e2229248a1eb835cc5ca46738723ed32481e08474fc",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/sv/qwen2-5-vl-3b-instruct/",
    "description": "Qwen2.5-VL-3B-Instruct är Qwens kompakta instruktionsanpassade modell för bild och språk, avsedd för text, bilder och video. Den returnerar text och strukturerad visuell information, inklusive dokumentfält, objektkoordinater och händelsebeskrivningar, med dynamisk upplösning och tidsmedveten videobearbetning.",
    "locale": "sv",
    "md_url": "https://ailoot.ai/models/sv/qwen2-5-vl-3b-instruct/index.md",
    "title": "Qwen2.5-VL-3b — Ailoot",
    "url": "https://ailoot.ai/models/sv/qwen2-5-vl-3b-instruct/"
  },
  "practicalHtml": "<h3>Praktisk uppgift</h3><p>Tekniskt exempel på engelska</p><pre><code>Organize a recorded event timeline\n\nUse only these text annotations from a clip: 00:02 worker picks up a box; 00:05 worker places the box on the scale; 00:08 scale display is obscured; 00:11 worker removes the box. Return the event sequence, the first annotated placement time and whether the weight is established. Preserve timestamps without claiming frame-level inspection.</code></pre><h4>Förväntat resultat</h4><pre><code>An ordered event table, a placement-time field and an unresolved weight field.</code></pre><h4>Kontrollera resultatet</h4><pre><code>Check that obscured weight remains unknown and the placement timestamp is attributed to the supplied annotation.</code></pre>",
  "practicalText": "Praktisk uppgift Tekniskt exempel på engelska Organize a recorded event timeline Use only these text annotations from a clip: 00:02 worker picks up a box; 00:05 worker places the box on the scale; 00:08 scale display is obscured; 00:11 worker removes the box. Return the event sequence, the first annotated placement time and whether the weight is established. Preserve timestamps without claiming frame-level inspection. Förväntat resultat An ordered event table, a placement-time field and an unresolved weight field. Kontrollera resultatet Check that obscured weight remains unknown and the placement timestamp is attributed to the supplied annotation.",
  "rawModel": {
    "about": "Inledning: den instruktionsanpassade 3B-utgåvan\n\nQwen2.5-VL-3B-Instruct är 3B-medlemmen i Qwen2.5-VL. Den tar emot textinstruktioner med bilder eller video och genererar textsvar, inklusive strukturerade data. Välj den för en tydligt definierad visuell fråga, en dokumentextraktionsuppgift eller en förklaring som kopplar synligt innehåll till användarens begäran. Exakt denna storlek och utgåva behåller sin egen identitet; funktioner som lagts till särskilt för andra storlekar eller senare Qwen-generationer bör inte antas gälla denna kontrollpunkt.\n\nVisuell förståelse och agentflöden\n\nQwen beskriver igenkänning av vanliga objekt och analys av skrift, diagram, ikoner, grafik och sidlayout. För ett formulär ska nödvändiga fält och betydelsen av ett tomt värde anges. För ett diagram ska axlar, enheter och synliga värden som stöder slutsatsen efterfrågas. En fokuserad begäran gör resultatet lättare att jämföra med originalbilden än en bred begäran att beskriva allt.\n\nFamiljen stöder också resonemang som visuell agent och styrning av verktyg för dator- eller telefonflöden. Modellen kan tolka ett gränssnitt och bidra till ett åtgärdsbeslut; anslutna applikationsverktyg utför åtgärden. En skärmbildsgranskning kan fråga vilken kontroll som motsvarar en uppgift och vilken synlig information som stöder valet. Den användningen av visuellt resonemang ger inte i sig kontroll över en enhet.\n\nLång video och händelselokalisering\n\nTillverkaren beskriver förståelse av videor längre än en timme och identifiering av segment som är relevanta för en begärd händelse. Det är en familjeförmåga, inte en ovillkorlig gräns för medieuppladdning eller en garanti att varje bildruta behålls. Förbered det relevanta klippet, bevara tidsinformationen och ställ en precis fråga om händelsen, sekvensen eller förändringen. Modellens videobearbetning använder bildfrekvensinformation för att anpassa visuella observationer till absolut tid.\n\nLokalisering och strukturerade dokument\n\nQwen2.5-VL kan returnera objektplatser som begränsningsrutor eller punkter, med koordinater och attribut i JSON. För en lokaliseringsuppgift ska målobjektet namnges och det anges om resultatet ska vara en punkt eller en ruta. Håll koordinatkonventionen uttrycklig i den konsumerande applikationen i stället för att härleda ett fysiskt mått ur ett godtyckligt fotografi.\n\nTillverkaren dokumenterar även strukturerad extraktion från skannade fakturor, formulär och tabeller. Tillhandahåll en läsbar sida och ett utdataschema: exempelvis fältnamn, extraherad text och det synliga område som stöder den. Bevara enheter, decimaltecken och tabellrubriker i källan. Behandla osäkert eller oläsligt innehåll som ett granskningsfall i stället för att be modellen hitta på ett saknat värde. Dessa förberedelseexempel tillämpar dokumenterade förmågor; de är inga garantier för exakt extraktion.\n\nArkitekturändringar\n\nDynamisk bildupplösning utvidgas till video genom träning med varierande bildfrekvens. Uppdaterad multimodal positionskodning representerar tidssekvens och absolut tid och hjälper till att identifiera specifika ögonblick och hastighetsförändringar. Bildkodaren använder window attention tillsammans med SwiGLU och RMSNorm. Ändringarna beskriver hur modellen bearbetar visuellt material; de fastställer ingen bestämd latens för en viss applikation.\n\nFörbereda bilder och video\n\nDe officiella exemplen omfattar enskilda bilder, flera bilder, rena textsamtal, videofiler och ordnade listor med bildrutor. Märk flera visuella indata så att en fråga kan hänvisa till var och en. För en bildjämförelse ska en tabell organiserad efter etiketterna begäras och resultatet begränsas till synliga skillnader. För en videotidslinje ska bildrutornas ordning och timing bevaras i stället för att fristående bilder presenteras som om de hade en känd varaktighet.\n\nBildprocessorns dokumenterade standardintervall går från fyra till 16,384 visuella token per bild. Exemplet kan sikta på 256–1,280 token genom att sätta pixelgränser. Det bevarar bildförhållandet inom gränserna, medan uttryckliga ändrade mått anpassas till multiplar av 28. Fler detaljer kräver mer beräkning och sekvensutrymme, så ett litet textfält kan behöva ett utsnitt med högre upplösning medan en bred scenbeskrivning kanske inte gör det. Detta är tillverkarens bearbetningskontroller; applikationens uppladdningsalternativ kan skilja sig.\n\nKontext och väsentliga begränsningar\n\nDen publicerade kontrollpunktskonfigurationen anger högsta antal positioner till 128,000, medan det medföljande avsnittet om lång text fortfarande diskuterar en startkonfiguration på 32,768 token. Guiden beskriver YaRN-extrapolering men varnar för att den kan påverka temporal och spatial lokalisering avsevärt och rekommenderar inte metoden för dessa uppgifter. Den nämner separat att positionskodning för video kan tillåta en större positionsinställning, med 64K som exempel. Dessa olika konfigurationsbeskrivningar bör inte sammanföras till ett enda universellt validerat indatatak.\n\nText, visuellt material och svar delar en ändlig sekvensbudget. Håll relevant innehåll läsligt, reservera plats för resultatet och kontrollera extraherad text, koordinater och händelsetider mot originalet. Modellkortets genereringsexempel med 128 token är illustrativt och fastställer ingen separat hård utdatagräns. Modellen returnerar textanalys eller strukturerad information; dess förmågor för bild och språk innebär inte att den genererar bilder eller video.",
    "alias_of": null,
    "aliases": [],
    "author": "Alibaba",
    "available": null,
    "canonical_model": "qwen2.5-vl-3b-instruct",
    "capabilities": {
      "context_length": 128000,
      "manufacturer_input": [],
      "manufacturer_output": []
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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": "qwen2.5-vl-3b-instruct",
    "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": [
                  "qwen2.5-vl-3b-instruct"
                ],
                "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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\": \"qwen2.5-vl-3b-instruct\", \"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='qwen2.5-vl-3b-instruct',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='qwen2.5-vl-3b-instruct',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": 0.4,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 1.2,
        "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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": "qwen2.5-vl-3b-instruct",
              "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": [
                  "qwen2.5-vl-3b-instruct"
                ],
                "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": [
                    "qwen2.5-vl-3b-instruct"
                  ],
                  "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": "qwen2.5-vl-3b-instruct",
              "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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\": \"qwen2.5-vl-3b-instruct\",\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': 'qwen2.5-vl-3b-instruct', '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': 'qwen2.5-vl-3b-instruct', '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": 0.4,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 1.2,
        "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": "0.0004000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000004",
                "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": "0.0012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000012",
                "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": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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": "qwen2.5-vl-3b-instruct",
        "request_model_id": "qwen2.5-vl-3b-instruct",
        "route_label": "Ultra"
      }
    ],
    "name": "Qwen2.5-VL-3b",
    "price": {
      "in": 0.4,
      "in_label": null,
      "out": 1.2,
      "out_label": null,
      "scope_label": "Token rates",
      "sort_in": 0.4,
      "sort_out": 1.2,
      "varies": false
    },
    "pricing_profiles": [
      {
        "dimensions": {
          "regime": "base"
        },
        "label": "OpenAI Chat · Base token rates",
        "units": [
          {
            "amount": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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": "0.0004000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000004",
            "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": "0.0012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000012",
            "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": "qwen2.5-vl-3b-instruct",
    "short": "Qwen2.5-VL-3B-Instruct är Qwens kompakta instruktionsanpassade modell för bild och språk, avsedd för text, bilder och video. Den returnerar text och strukturerad visuell information, inklusive dokumentfält, objektkoordinater och händelsebeskrivningar, med dynamisk upplösning och tidsmedveten videobearbetning."
  },
  "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": "Qwen2.5-VL-3B-Instruct är Qwens kompakta instruktionsanpassade modell för bild och språk, avsedd för text, bilder och video. Den returnerar text och strukturerad visuell information, inklusive dokumentfält, objektkoordinater och händelsebeskrivningar, med dynamisk upplösning och tidsmedveten videobearbetning.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "f1c91911e5a813f507128405e668a83c27210d205a3c858323083c6bf4b92a7b",
    "renderer_sha256": "8a45bb31b83d2551e6d975cf4683518c7cb445a54b9394a01947f4dd103f1051"
  },
  "sourceRevision": "58150fb3d21aaa7539780261f08c290f4d8d4d545e05aa829868e71c00391b92"
}