{
  "aboutHtml": "<p>Llama Nemotron Rerank VL 1B V2 ocenjuje relevantnost kandidatnih besedil in slik dokumentov za besedilno poizvedbo, vključno z grafikoni, tabelami in stranmi z mešanimi mediji. NVIDIA ga opisuje kot model s križnim kodirnikom z 1,7 milijarde parametrov. V postopku pridobivanja najprej izvedite začetno iskanje, nato pa izbrane kandidate pošljite modelu za ponovno razvrščanje. Uporabni rezultat je preurejen niz teh kandidatov z ocenami relevantnosti, ki jih aplikacija lahko uporabi za izbiro konteksta odgovora ali urejanje strani z rezultati iskanja.</p><p>Uporabite POST /v1/rerank s telesom application/json. model nastavite na &quot;nvidia/llama-nemotron-rerank-vl-1b-v2:free&quot;, query na dejansko iskalno vprašanje, documents pa na neprazno polje. Vsak kandidat je lahko besedilni niz ali objekt s text in/ali image; strukturirani objekt mora vsebovati vsaj eno od teh polj. text je niz. image je oddaljeni URL HTTP/HTTPS ali podatkovni URI base64, ki se začne z data:image/. Kombinirani kandidat vsebuje obe polji. Ohranite vrstni red tega vhodnega polja, da lahko vrnjene indekse povežete s shranjenimi ID-ji dokumentov. top_n je izbirno celo število z vrednostjo najmanj 1, ki zahteva število najbolje razvrščenih dokumentov za vrnitev.</p><p>Aplikacija centra za pomoč lahko na primer pridobi odlomke o dostavi, vračilih in dostopu do računa, nato pa jih ponovno razvrsti glede na strankino vprašanje o dostavi. Podajte dejansko besedilo odlomkov namesto imen datotek ali izsekov iskalnika, ki niso povezani s shranjenim virom. Vsak odlomek v aplikaciji povežite z lastnim izvornim identifikatorjem, da bo izbrane dokaze pozneje mogoče navesti ali odpreti. Pri skeniranem dokumentu, grafikonu, tabeli ali infografiki podajte dejansko sliko v objektu dokumenta in dodajte besedilo, kadar pomaga prepoznati vsebino.</p><p>Stran modela dokumentira omejitev 10 240 žetonov na poizvedbo in dokument. Daljše izvorno gradivo pred pripravo seznama kandidatov razdelite na omejene odlomke. Ob vsakem odlomku ohranite uporaben okoliški kontekst, vključno z naslovom ali imenom izdelka, kadar spreminja pomen. Dokumentirana zahteva izhaja iz kandidatov, ki jih podate; zbirke dokumentov ne preišče namesto vas.</p><p>Ponovno razvrščanje vrne sinhroni rezultat JSON. Preberite vsak element results, vključno z njegovim izvirnim indeksom index, oceno relevance_score in vrnjenim objektom document, ki lahko vsebuje text in/ali image, ter ohranite vse vrnjene podatke usage in identifikatorje odgovora. Z vrednostjo index razvrščeni rezultat preslikajte nazaj na njegovega vhodnega kandidata. Oceno relevantnosti obravnavajte kot signal razvrstitve za to poizvedbo in ne kot neodvisno preverjen dejstveni odgovor. Kadar za naslednji korak izberete več odlomkov, ohranite celotni rezultat.</p><p>Za to brezplačno izdajo pripravite javno ali sintetično kandidatno gradivo; njeni dokumentirani pogoji uporabe izključujejo zaupne informacije in osebne podatke. Če se zahteva konča brez celotnega rezultata, med preverjanjem tega poskusa ohranite izvirni odgovor in identifikator zahteve. Dokumentirani postopek ponovnega razvrščanja rezultat vrne neposredno ter ne ponuja ločenega preverjanja stanja opravila ali postopka preklica.</p>",
  "aboutText": "Llama Nemotron Rerank VL 1B V2 ocenjuje relevantnost kandidatnih besedil in slik dokumentov za besedilno poizvedbo, vključno z grafikoni, tabelami in stranmi z mešanimi mediji. NVIDIA ga opisuje kot model s križnim kodirnikom z 1,7 milijarde parametrov. V postopku pridobivanja najprej izvedite začetno iskanje, nato pa izbrane kandidate pošljite modelu za ponovno razvrščanje. Uporabni rezultat je preurejen niz teh kandidatov z ocenami relevantnosti, ki jih aplikacija lahko uporabi za izbiro konteksta odgovora ali urejanje strani z rezultati iskanja.\n\nUporabite POST /v1/rerank s telesom application/json. model nastavite na \"nvidia/llama-nemotron-rerank-vl-1b-v2:free\", query na dejansko iskalno vprašanje, documents pa na neprazno polje. Vsak kandidat je lahko besedilni niz ali objekt s text in/ali image; strukturirani objekt mora vsebovati vsaj eno od teh polj. text je niz. image je oddaljeni URL HTTP/HTTPS ali podatkovni URI base64, ki se začne z data:image/. Kombinirani kandidat vsebuje obe polji. Ohranite vrstni red tega vhodnega polja, da lahko vrnjene indekse povežete s shranjenimi ID-ji dokumentov. top_n je izbirno celo število z vrednostjo najmanj 1, ki zahteva število najbolje razvrščenih dokumentov za vrnitev.\n\nAplikacija centra za pomoč lahko na primer pridobi odlomke o dostavi, vračilih in dostopu do računa, nato pa jih ponovno razvrsti glede na strankino vprašanje o dostavi. Podajte dejansko besedilo odlomkov namesto imen datotek ali izsekov iskalnika, ki niso povezani s shranjenim virom. Vsak odlomek v aplikaciji povežite z lastnim izvornim identifikatorjem, da bo izbrane dokaze pozneje mogoče navesti ali odpreti. Pri skeniranem dokumentu, grafikonu, tabeli ali infografiki podajte dejansko sliko v objektu dokumenta in dodajte besedilo, kadar pomaga prepoznati vsebino.\n\nStran modela dokumentira omejitev 10 240 žetonov na poizvedbo in dokument. Daljše izvorno gradivo pred pripravo seznama kandidatov razdelite na omejene odlomke. Ob vsakem odlomku ohranite uporaben okoliški kontekst, vključno z naslovom ali imenom izdelka, kadar spreminja pomen. Dokumentirana zahteva izhaja iz kandidatov, ki jih podate; zbirke dokumentov ne preišče namesto vas.\n\nPonovno razvrščanje vrne sinhroni rezultat JSON. Preberite vsak element results, vključno z njegovim izvirnim indeksom index, oceno relevance_score in vrnjenim objektom document, ki lahko vsebuje text in/ali image, ter ohranite vse vrnjene podatke usage in identifikatorje odgovora. Z vrednostjo index razvrščeni rezultat preslikajte nazaj na njegovega vhodnega kandidata. Oceno relevantnosti obravnavajte kot signal razvrstitve za to poizvedbo in ne kot neodvisno preverjen dejstveni odgovor. Kadar za naslednji korak izberete več odlomkov, ohranite celotni rezultat.\n\nZa to brezplačno izdajo pripravite javno ali sintetično kandidatno gradivo; njeni dokumentirani pogoji uporabe izključujejo zaupne informacije in osebne podatke. Če se zahteva konča brez celotnega rezultata, med preverjanjem tega poskusa ohranite izvirni odgovor in identifikator zahteve. Dokumentirani postopek ponovnega razvrščanja rezultat vrne neposredno ter ne ponuja ločenega preverjanja stanja opravila ali postopka preklica.",
  "editorialOverlay": {
    "copy_fields": null,
    "copy_sha256": null,
    "copy_source": null,
    "html_sha256": "fe36cf2fcd5ac21e9201976e66966b99e29f13b3a231120a5aa85347fb77146f",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "sl",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">NV</span><h2 id=\"sheet-title\">NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Zapri\">×</button></div><div class=\"idline\"><span>NVIDIA /</span><code>nvidia/llama-nemotron-rerank-vl-1b-v2:free</code><button type=\"button\" id=\"copy-id\">Kopiraj ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Razdelki kartice modela\"><button type=\"button\" data-card-jump=\"overview\">Začetek</button><button type=\"button\" data-card-jump=\"methods\">Vhodi in metode</button><button type=\"button\" data-card-jump=\"pricing\">Cenik</button><button type=\"button\" data-card-jump=\"examples\">Primeri</button><button type=\"button\" data-card-jump=\"results\">Rezultati</button><button type=\"button\" data-card-jump=\"aliases\">Druga imena</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"Metode API\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Ultra|rerank|/v1/rerank|nvidia%2Fllama-nemotron-rerank-vl-1b-v2%3Afree\">Ponovno razvrščanje</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\">Začetek</h3><p class=\"mdesc-full\">Llama Nemotron Rerank VL 1B V2 je model NVIDIA za ponovno razvrščanje s križnim kodirnikom, ki pridobljeno gradivo uredi po relevantnosti za poizvedbo. Pošljite poizvedbo in kandidatne besedilne, slikovne ali kombinirane dokumente, nato pa z vrnjenimi ocenami in izvirnimi indeksi izberite odlomke za rezultate iskanja ali odgovor, dopolnjen s pridobljenimi viri.</p><dl class=\"card-io\" data-card-io><div><dt>Dovoljeni vhodi</dt><dd>Besedilo</dd></div><div><dt>Rezultati</dt><dd>ranking</dd></div></dl><details class=\"card-about\"><summary>O modelu</summary><p class=\"note-s\" data-model-method-boundary>Ta opis zajema zmožnosti modela. Vhodi, izhodi in možnosti, ki so na voljo v Ailoot, so spodaj navedeni za izbrano metodo.</p><div class=\"mabout\" id=\"m-about\"><p>Llama Nemotron Rerank VL 1B V2 ocenjuje relevantnost kandidatnih besedil in slik dokumentov za besedilno poizvedbo, vključno z grafikoni, tabelami in stranmi z mešanimi mediji. NVIDIA ga opisuje kot model s križnim kodirnikom z 1,7 milijarde parametrov. V postopku pridobivanja najprej izvedite začetno iskanje, nato pa izbrane kandidate pošljite modelu za ponovno razvrščanje. Uporabni rezultat je preurejen niz teh kandidatov z ocenami relevantnosti, ki jih aplikacija lahko uporabi za izbiro konteksta odgovora ali urejanje strani z rezultati iskanja.</p><p>Uporabite POST /v1/rerank s telesom application/json. model nastavite na &quot;nvidia/llama-nemotron-rerank-vl-1b-v2:free&quot;, query na dejansko iskalno vprašanje, documents pa na neprazno polje. Vsak kandidat je lahko besedilni niz ali objekt s text in/ali image; strukturirani objekt mora vsebovati vsaj eno od teh polj. text je niz. image je oddaljeni URL HTTP/HTTPS ali podatkovni URI base64, ki se začne z data:image/. Kombinirani kandidat vsebuje obe polji. Ohranite vrstni red tega vhodnega polja, da lahko vrnjene indekse povežete s shranjenimi ID-ji dokumentov. top_n je izbirno celo število z vrednostjo najmanj 1, ki zahteva število najbolje razvrščenih dokumentov za vrnitev.</p><p>Aplikacija centra za pomoč lahko na primer pridobi odlomke o dostavi, vračilih in dostopu do računa, nato pa jih ponovno razvrsti glede na strankino vprašanje o dostavi. Podajte dejansko besedilo odlomkov namesto imen datotek ali izsekov iskalnika, ki niso povezani s shranjenim virom. Vsak odlomek v aplikaciji povežite z lastnim izvornim identifikatorjem, da bo izbrane dokaze pozneje mogoče navesti ali odpreti. Pri skeniranem dokumentu, grafikonu, tabeli ali infografiki podajte dejansko sliko v objektu dokumenta in dodajte besedilo, kadar pomaga prepoznati vsebino.</p><p>Stran modela dokumentira omejitev 10 240 žetonov na poizvedbo in dokument. Daljše izvorno gradivo pred pripravo seznama kandidatov razdelite na omejene odlomke. Ob vsakem odlomku ohranite uporaben okoliški kontekst, vključno z naslovom ali imenom izdelka, kadar spreminja pomen. Dokumentirana zahteva izhaja iz kandidatov, ki jih podate; zbirke dokumentov ne preišče namesto vas.</p><p>Ponovno razvrščanje vrne sinhroni rezultat JSON. Preberite vsak element results, vključno z njegovim izvirnim indeksom index, oceno relevance_score in vrnjenim objektom document, ki lahko vsebuje text in/ali image, ter ohranite vse vrnjene podatke usage in identifikatorje odgovora. Z vrednostjo index razvrščeni rezultat preslikajte nazaj na njegovega vhodnega kandidata. Oceno relevantnosti obravnavajte kot signal razvrstitve za to poizvedbo in ne kot neodvisno preverjen dejstveni odgovor. Kadar za naslednji korak izberete več odlomkov, ohranite celotni rezultat.</p><p>Za to brezplačno izdajo pripravite javno ali sintetično kandidatno gradivo; njeni dokumentirani pogoji uporabe izključujejo zaupne informacije in osebne podatke. Če se zahteva konča brez celotnega rezultata, med preverjanjem tega poskusa ohranite izvirni odgovor in identifikator zahteve. Dokumentirani postopek ponovnega razvrščanja rezultat vrne neposredno ter ne ponuja ločenega preverjanja stanja opravila ali postopka preklica.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Na voljo v Ailoot · vhodi in metode</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Rerank</b> <code>POST /v1/rerank</code></summary><dl class=\"method-capabilities\"><div><dt>Vhod</dt><dd><code>text</code></dd></div><div><dt>Izhod</dt><dd><code>ranking</code></dd></div><div><dt>Izhodni format</dt><dd>JSON</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Polje</th><th>Vrsta</th><th>Zahteva</th><th>Vrednosti in omejitve</th><th>Privzeto</th></tr></thead><tbody><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>string</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Obvezno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span><div>nvidia/llama-nemotron-rerank-vl-1b-v2:free</div></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">query</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>string</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Obvezno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">documents</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>array</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Obvezno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">top_n</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>integer</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Izbirno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span><div>Najmanj: 1</div></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr></tbody></table></div><details class=\"note-s\" data-method-contract><summary>Parametri in življenjski cikel metode</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Specifikacija</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=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</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=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>model, query, documents</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>optional</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>top_n</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=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>text</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>conditions</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span></td></tr></tbody></table></div><p>Življenjski cikel: <code>synchronous_json</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Cenik</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Tarifni podatki ne dodajajo možnosti zahteve. Podprti parametri so navedeni pri izbrani metodi.</p><dl data-price-conditions><dt>Hitri način</dt><dd>Ni navedeno <span class=\"note-s\">Ko je izbran hitri način</span></dd><dt>Način flex</dt><dd>Ni navedeno <span class=\"note-s\">Ko je izbran način flex</span></dd><dt>Najvišja raven razmišljanja</dt><dd>Ni navedeno <span class=\"note-s\">Ko najvišja raven razmišljanja uporablja privzeto prilagoditev (default)</span></dd></dl></div><div data-declared-tariff-pricing><h4>Cene Ailoot</h4><h4>Cene po nastavitvah</h4><p class=\"note-s\">Vsak strošek povežite s prikazanimi pogoji. Za vsak nabor alternativnih nastavitev uporabite eno ceno.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Nastavitev</th><th>Cenovna lestvica</th><th>Obračunska količina</th><th>Strošek</th></tr></thead><tbody><tr><th data-cell-label=\"Nastavitev\" scope=\"row\"><span class=\"card-cell-label\">Nastavitev</span>Osnovne cene žetonov</th><td data-cell-label=\"Cenovna lestvica\"><span class=\"card-cell-label\">Cenovna lestvica</span>Osnovna cena</td><td data-cell-label=\"Obračunska količina\"><span class=\"card-cell-label\">Obračunska količina</span>—</td><td data-cell-label=\"Strošek\"><span class=\"card-cell-label\">Strošek</span><div><span>Vhod · Vhodni žetoni</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Izhod · Izhodni žetoni</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Vhod · Branje predpomnilnika</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Vhod · Zapis v predpomnilnik</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Vhod · Zapis v predpomnilnik, 1 ura</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div></td></tr><tr><th data-cell-label=\"Nastavitev\" scope=\"row\"><span class=\"card-cell-label\">Nastavitev</span>Na zahtevo</th><td data-cell-label=\"Cenovna lestvica\"><span class=\"card-cell-label\">Cenovna lestvica</span>—</td><td data-cell-label=\"Obračunska količina\"><span class=\"card-cell-label\">Obračunska količina</span>ena zahteva</td><td data-cell-label=\"Strošek\"><span class=\"card-cell-label\">Strošek</span><div><span>Vhod</span> <b>$0</b> <span class=\"price-unit\">na zahtevo</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot pred zahtevo rezervira ocenjeni znesek. Po rezultatu obračuna končni strošek na podlagi izmerjene porabe. Obračun pretakanja uporablja končni zapis porabe. <a href=\"/docs/sl/billing/reserve/\">Kako delujeta rezervacija in obračun →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Primeri zahtev</h3><h4>Ailoot Ultra · Rerank</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Primeri kode\"><button class=\"cg-tab\" id=\"model-code-32-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-32-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl · ustvarite enkrat in ohranite celoten rezultat</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiraj kodo\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-32-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-32-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\nexport AILOOT_API_KEY\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;documents&quot;: [&quot;Paris is the capital of France.&quot;, &quot;Berlin is the capital of Germany.&quot;], &quot;model&quot;: &quot;nvidia/llama-nemotron-rerank-vl-1b-v2:free&quot;, &quot;query&quot;: &quot;What is the capital of France?&quot;, &quot;top_n&quot;: 3}&#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/rerank \\\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\n# Submit once. Retain the complete result, original identifiers and every response header.\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Prejmi in shrani rezultate</h3><h4>Ailoot Ultra · Rerank</h4><p class=\"note-s\">JSON</p><div class=\"card-result-process\" data-all-results><h5>Ohrani vse dokončane rezultate</h5><p class=\"note-s\">Shranite vsak v celoti vrnjen odgovor, datoteko in del vsebine.</p><p class=\"note-s\">Retain the complete response, all actual results, original identifiers, usage and response headers.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Če je treba preveriti izvirni odgovor</h5><p class=\"note-s\">Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.</p></div><details class=\"card-about\" data-output-fields><summary>Polja odgovora</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Polje</th><th>Vrsta</th></tr></thead><tbody><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">results</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>array</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Druga imena</h3><h4>Druga imena modelov</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=nvidia%2Fllama-nemotron-rerank-vl-1b-v2%3Afree&amp;route=Ultra&amp;caller=nvidia%2Fllama-nemotron-rerank-vl-1b-v2%3Afree&amp;fmt=rerank\"><code>nvidia/llama-nemotron-rerank-vl-1b-v2:free</code></a></span></p><h4>Druga imena poti metod</h4><p class=\"note-s\">Uporabite zgoraj navedene poti metod.</p><h4>Povezani ID-ji za klic</h4><p class=\"note-s\"><a href=\"#m=nvidia%2Fllama-nemotron-rerank-vl-1b-v2%3Afree&amp;route=Ultra&amp;caller=nvidia%2Fllama-nemotron-rerank-vl-1b-v2%3Afree&amp;fmt=rerank\"><code>nvidia/llama-nemotron-rerank-vl-1b-v2:free</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
        "fmt": "rerank",
        "http": "POST",
        "path": "/v1/rerank",
        "request_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|rerank|/v1/rerank|nvidia%2Fllama-nemotron-rerank-vl-1b-v2%3Afree",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "example_body": {
              "documents": [
                "Paris is the capital of France.",
                "Berlin is the capital of Germany."
              ],
              "model": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
              "query": "What is the capital of France?",
              "top_n": 3
            },
            "lifecycle": {
              "cancel_endpoint": null,
              "create": {
                "http": "POST",
                "path": "/v1/rerank"
              },
              "mode": "synchronous_json",
              "status": [],
              "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.",
              "unknown_no_replay": true
            },
            "outputs": {
              "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.",
              "family": "ranking",
              "fields": [
                {
                  "name": "results",
                  "type": "array"
                }
              ],
              "format": "JSON"
            },
            "parameters": [
              {
                "default_known": false,
                "enum": [
                  "nvidia/llama-nemotron-rerank-vl-1b-v2:free"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "default_known": false,
                "enum_known": false,
                "name": "query",
                "required": true,
                "type": "string"
              },
              {
                "default_known": false,
                "enum_known": false,
                "items": {
                  "type": "string"
                },
                "minItems": 1,
                "name": "documents",
                "required": true,
                "type": "array"
              },
              {
                "default_known": false,
                "enum_known": false,
                "minimum": 1,
                "name": "top_n",
                "required": false,
                "type": "integer"
              }
            ],
            "request_schema": {
              "additionalProperties": true,
              "properties": {
                "documents": {
                  "items": {
                    "type": "string"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "nvidia/llama-nemotron-rerank-vl-1b-v2:free"
                  ],
                  "type": "string"
                },
                "query": {
                  "type": "string"
                },
                "top_n": {
                  "minimum": 1,
                  "type": "integer"
                }
              },
              "required": [
                "model",
                "query",
                "documents"
              ],
              "type": "object"
            },
            "schema_template": {
              "body": {
                "documents": [
                  "Paris is the capital of France.",
                  "Berlin is the capital of Germany."
                ],
                "model": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
                "query": "What is the capital of France?",
                "top_n": 3
              },
              "content_type": "application/json"
            }
          },
          "input": {
            "conditions": [],
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional": [
              "top_n"
            ],
            "required": [
              "model",
              "query",
              "documents"
            ]
          },
          "lifecycle": {
            "cancel_endpoint": null,
            "create": {
              "http": "POST",
              "path": "/v1/rerank"
            },
            "mode": "synchronous_json",
            "status": [],
            "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.",
            "unknown_no_replay": true
          },
          "method": {
            "http": "POST",
            "path": "/v1/rerank"
          },
          "method_aliases": [],
          "output": {
            "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.",
            "family": "ranking",
            "fields": [
              {
                "name": "results",
                "type": "array"
              }
            ],
            "format": "JSON"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "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": {
              "billing_quantity": "one request"
            },
            "label": "Per request",
            "units": [
              {
                "amount": "0",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": true,
                "estimate_only": false,
                "key": "per_request",
                "label": "per request",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "public_unit_label": "per request",
                "quantity": 1,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "per_request"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"documents\": [\"Paris is the capital of France.\", \"Berlin is the capital of Germany.\"], \"model\": \"nvidia/llama-nemotron-rerank-vl-1b-v2:free\", \"query\": \"What is the capital of France?\", \"top_n\": 3}')\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/rerank \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n",
            "label": "curl · create once and retain the complete result",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "rerank",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": null,
        "input": [
          "text"
        ],
        "label": "Rerank",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": null,
        "output": [
          "ranking"
        ],
        "path": "/v1/rerank",
        "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": "per_request",
          "cache_read_price": null,
          "cache_write_1h_price": null,
          "cache_write_price": null,
          "fast_multiplier": null,
          "flex_multiplier": null,
          "image_input_price": null,
          "image_output_price": null,
          "input_price": null,
          "intervals": null,
          "max_reasoning_effort_multiplier": null,
          "output_price": null,
          "per_request_price": 0
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "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": {
              "billing_quantity": "one request"
            },
            "label": "Per request",
            "units": [
              {
                "amount": "0",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": true,
                "estimate_only": false,
                "key": "per_request",
                "label": "per request",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "public_unit_label": "per request",
                "quantity": 1,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "per_request"
              }
            ]
          }
        ],
        "request_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "unit": "per_request",
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "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": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "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": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "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": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "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"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": true,
            "estimate_only": false,
            "key": "per_request",
            "label": "per request",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "public_unit_label": "per request",
            "quantity": 1,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "per_request"
          }
        ]
      }
    }
  ],
  "model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "db75752cde89b88e03e542aaa3a3d2db82032b1af041a869ee3a4ddde06e6414",
    "input_html_sha256": "c20436c2ccea9c00f4ad5d6eceb54283fd7fd5303d32ea23b4b2ceb43365a610",
    "private_audit_sha256": "2626a94067b946aaeabd1b460f37fe6fd7a4114b54d6a803ff533d89404db50e",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/sl/nvidia-llama-nemotron-rerank-vl-1b-v2-u003a-free/",
    "description": "Llama Nemotron Rerank VL 1B V2 je model NVIDIA za ponovno razvrščanje s križnim kodirnikom, ki pridobljeno gradivo uredi po relevantnosti za poizvedbo. Pošljite poizvedbo in kandidatne besedilne, slikovne ali kombinirane dokumente, nato pa z vrnjenimi ocenami in izvirnimi indeksi izberite odlomke za rezultate iskanja ali odgovor, dopolnjen s pridobljenimi viri.",
    "locale": "sl",
    "md_url": "https://ailoot.ai/models/sl/nvidia-llama-nemotron-rerank-vl-1b-v2-u003a-free/index.md",
    "title": "NVIDIA: Llama Nemotron Rerank VL 1B V2 (free) — Ailoot",
    "url": "https://ailoot.ai/models/sl/nvidia-llama-nemotron-rerank-vl-1b-v2-u003a-free/"
  },
  "rawModel": {
    "about": "Llama Nemotron Rerank VL 1B V2 ocenjuje relevantnost kandidatnih besedil in slik dokumentov za besedilno poizvedbo, vključno z grafikoni, tabelami in stranmi z mešanimi mediji. NVIDIA ga opisuje kot model s križnim kodirnikom z 1,7 milijarde parametrov. V postopku pridobivanja najprej izvedite začetno iskanje, nato pa izbrane kandidate pošljite modelu za ponovno razvrščanje. Uporabni rezultat je preurejen niz teh kandidatov z ocenami relevantnosti, ki jih aplikacija lahko uporabi za izbiro konteksta odgovora ali urejanje strani z rezultati iskanja.\n\nUporabite POST /v1/rerank s telesom application/json. model nastavite na \"nvidia/llama-nemotron-rerank-vl-1b-v2:free\", query na dejansko iskalno vprašanje, documents pa na neprazno polje. Vsak kandidat je lahko besedilni niz ali objekt s text in/ali image; strukturirani objekt mora vsebovati vsaj eno od teh polj. text je niz. image je oddaljeni URL HTTP/HTTPS ali podatkovni URI base64, ki se začne z data:image/. Kombinirani kandidat vsebuje obe polji. Ohranite vrstni red tega vhodnega polja, da lahko vrnjene indekse povežete s shranjenimi ID-ji dokumentov. top_n je izbirno celo število z vrednostjo najmanj 1, ki zahteva število najbolje razvrščenih dokumentov za vrnitev.\n\nAplikacija centra za pomoč lahko na primer pridobi odlomke o dostavi, vračilih in dostopu do računa, nato pa jih ponovno razvrsti glede na strankino vprašanje o dostavi. Podajte dejansko besedilo odlomkov namesto imen datotek ali izsekov iskalnika, ki niso povezani s shranjenim virom. Vsak odlomek v aplikaciji povežite z lastnim izvornim identifikatorjem, da bo izbrane dokaze pozneje mogoče navesti ali odpreti. Pri skeniranem dokumentu, grafikonu, tabeli ali infografiki podajte dejansko sliko v objektu dokumenta in dodajte besedilo, kadar pomaga prepoznati vsebino.\n\nStran modela dokumentira omejitev 10 240 žetonov na poizvedbo in dokument. Daljše izvorno gradivo pred pripravo seznama kandidatov razdelite na omejene odlomke. Ob vsakem odlomku ohranite uporaben okoliški kontekst, vključno z naslovom ali imenom izdelka, kadar spreminja pomen. Dokumentirana zahteva izhaja iz kandidatov, ki jih podate; zbirke dokumentov ne preišče namesto vas.\n\nPonovno razvrščanje vrne sinhroni rezultat JSON. Preberite vsak element results, vključno z njegovim izvirnim indeksom index, oceno relevance_score in vrnjenim objektom document, ki lahko vsebuje text in/ali image, ter ohranite vse vrnjene podatke usage in identifikatorje odgovora. Z vrednostjo index razvrščeni rezultat preslikajte nazaj na njegovega vhodnega kandidata. Oceno relevantnosti obravnavajte kot signal razvrstitve za to poizvedbo in ne kot neodvisno preverjen dejstveni odgovor. Kadar za naslednji korak izberete več odlomkov, ohranite celotni rezultat.\n\nZa to brezplačno izdajo pripravite javno ali sintetično kandidatno gradivo; njeni dokumentirani pogoji uporabe izključujejo zaupne informacije in osebne podatke. Če se zahteva konča brez celotnega rezultata, med preverjanjem tega poskusa ohranite izvirni odgovor in identifikator zahteve. Dokumentirani postopek ponovnega razvrščanja rezultat vrne neposredno ter ne ponuja ločenega preverjanja stanja opravila ali postopka preklica.",
    "alias_of": null,
    "aliases": [],
    "author": "NVIDIA",
    "ctx": 10240,
    "formats": [
      "rerank"
    ],
    "id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
    "input": [
      "text"
    ],
    "kind": "text",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "example_body": {
              "documents": [
                "Paris is the capital of France.",
                "Berlin is the capital of Germany."
              ],
              "model": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
              "query": "What is the capital of France?",
              "top_n": 3
            },
            "lifecycle": {
              "cancel_endpoint": null,
              "create": {
                "http": "POST",
                "path": "/v1/rerank"
              },
              "mode": "synchronous_json",
              "status": [],
              "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.",
              "unknown_no_replay": true
            },
            "outputs": {
              "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.",
              "family": "ranking",
              "fields": [
                {
                  "name": "results",
                  "type": "array"
                }
              ],
              "format": "JSON"
            },
            "parameters": [
              {
                "default_known": false,
                "enum": [
                  "nvidia/llama-nemotron-rerank-vl-1b-v2:free"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "default_known": false,
                "enum_known": false,
                "name": "query",
                "required": true,
                "type": "string"
              },
              {
                "default_known": false,
                "enum_known": false,
                "items": {
                  "type": "string"
                },
                "minItems": 1,
                "name": "documents",
                "required": true,
                "type": "array"
              },
              {
                "default_known": false,
                "enum_known": false,
                "minimum": 1,
                "name": "top_n",
                "required": false,
                "type": "integer"
              }
            ],
            "request_schema": {
              "additionalProperties": true,
              "properties": {
                "documents": {
                  "items": {
                    "type": "string"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "nvidia/llama-nemotron-rerank-vl-1b-v2:free"
                  ],
                  "type": "string"
                },
                "query": {
                  "type": "string"
                },
                "top_n": {
                  "minimum": 1,
                  "type": "integer"
                }
              },
              "required": [
                "model",
                "query",
                "documents"
              ],
              "type": "object"
            },
            "schema_template": {
              "body": {
                "documents": [
                  "Paris is the capital of France.",
                  "Berlin is the capital of Germany."
                ],
                "model": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
                "query": "What is the capital of France?",
                "top_n": 3
              },
              "content_type": "application/json"
            }
          },
          "input": {
            "conditions": [],
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional": [
              "top_n"
            ],
            "required": [
              "model",
              "query",
              "documents"
            ]
          },
          "lifecycle": {
            "cancel_endpoint": null,
            "create": {
              "http": "POST",
              "path": "/v1/rerank"
            },
            "mode": "synchronous_json",
            "status": [],
            "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.",
            "unknown_no_replay": true
          },
          "method": {
            "http": "POST",
            "path": "/v1/rerank"
          },
          "method_aliases": [],
          "output": {
            "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.",
            "family": "ranking",
            "fields": [
              {
                "name": "results",
                "type": "array"
              }
            ],
            "format": "JSON"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "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": {
              "billing_quantity": "one request"
            },
            "label": "Per request",
            "units": [
              {
                "amount": "0",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": true,
                "estimate_only": false,
                "key": "per_request",
                "label": "per request",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "public_unit_label": "per request",
                "quantity": 1,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "per_request"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"documents\": [\"Paris is the capital of France.\", \"Berlin is the capital of Germany.\"], \"model\": \"nvidia/llama-nemotron-rerank-vl-1b-v2:free\", \"query\": \"What is the capital of France?\", \"top_n\": 3}')\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/rerank \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n",
            "label": "curl · create once and retain the complete result",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "rerank",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": null,
        "input": [
          "text"
        ],
        "label": "Rerank",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": null,
        "output": [
          "ranking"
        ],
        "path": "/v1/rerank",
        "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": "per_request",
          "cache_read_price": null,
          "cache_write_1h_price": null,
          "cache_write_price": null,
          "fast_multiplier": null,
          "flex_multiplier": null,
          "image_input_price": null,
          "image_output_price": null,
          "input_price": null,
          "intervals": null,
          "max_reasoning_effort_multiplier": null,
          "output_price": null,
          "per_request_price": 0
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "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": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "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": {
              "billing_quantity": "one request"
            },
            "label": "Per request",
            "units": [
              {
                "amount": "0",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": true,
                "estimate_only": false,
                "key": "per_request",
                "label": "per request",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "public_unit_label": "per request",
                "quantity": 1,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "per_request"
              }
            ]
          }
        ],
        "request_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "unit": "per_request",
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "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": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "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": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "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": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "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"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": true,
            "estimate_only": false,
            "key": "per_request",
            "label": "per request",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "public_unit_label": "per request",
            "quantity": 1,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "per_request"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
        "request_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2:free",
        "route_label": "Ultra"
      }
    ],
    "name": "NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)",
    "price": {
      "in": "0",
      "in_label": "per request",
      "out": null,
      "out_label": null,
      "sort_in": null,
      "sort_out": null,
      "varies": false
    },
    "short": "Llama Nemotron Rerank VL 1B V2 je model NVIDIA za ponovno razvrščanje s križnim kodirnikom, ki pridobljeno gradivo uredi po relevantnosti za poizvedbo. Pošljite poizvedbo in kandidatne besedilne, slikovne ali kombinirane dokumente, nato pa z vrnjenimi ocenami in izvirnimi indeksi izberite odlomke za rezultate iskanja ali odgovor, dopolnjen s pridobljenimi viri."
  },
  "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
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "Llama Nemotron Rerank VL 1B V2 je model NVIDIA za ponovno razvrščanje s križnim kodirnikom, ki pridobljeno gradivo uredi po relevantnosti za poizvedbo. Pošljite poizvedbo in kandidatne besedilne, slikovne ali kombinirane dokumente, nato pa z vrnjenimi ocenami in izvirnimi indeksi izberite odlomke za rezultate iskanja ali odgovor, dopolnjen s pridobljenimi viri.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "006fa0e55e03345f3ad346b79e06c15c462f5a21263c1967c0a1da1a6a363989",
    "renderer_sha256": "dcba2271c18b0f9570a8b166e8d1e3166f121e096a58609c3a46da31562a1bf2"
  },
  "sourceRevision": "02f0bfb848d05bffeea0839d3d1d64783a22b23b89bf5d71f880d755a76d04e5"
}