{
  "aboutHtml": "<p>google/gemini-embedding-001 représente le texte par des vecteurs de recherche. Il peut retrouver un passage technique pertinent malgré une question formulée autrement. La route Ailoot annonce 20 000 tokens de contexte hébergé et accepte chaîne, tableau de chaînes ou tableau d’identifiants de tokens, avec un seul type cohérent par requête.</p><p>La réponse contient des vecteurs indexés de nombres flottants finis. Aucune largeur par défaut n’est publiée et la surcharge dimensions est explicitement exclue : établissez la largeur d’index depuis le vecteur retourné et gardez-la fixe. encoding_format accepte float. Aucun sélecteur de tâche ou requête/document n’est exposé. Préparez questions et documents de manière cohérente et conservez modèle exact et largeur ensemble dans l’index.</p>",
  "aboutText": "google/gemini-embedding-001 représente le texte par des vecteurs de recherche. Il peut retrouver un passage technique pertinent malgré une question formulée autrement. La route Ailoot annonce 20 000 tokens de contexte hébergé et accepte chaîne, tableau de chaînes ou tableau d’identifiants de tokens, avec un seul type cohérent par requête. La réponse contient des vecteurs indexés de nombres flottants finis. Aucune largeur par défaut n’est publiée et la surcharge dimensions est explicitement exclue : établissez la largeur d’index depuis le vecteur retourné et gardez-la fixe. encoding_format accepte float. Aucun sélecteur de tâche ou requête/document n’est exposé. Préparez questions et documents de manière cohérente et conservez modèle exact et largeur ensemble dans l’index.",
  "editorialOverlay": {
    "copy_fields": {
      "about_html": "<p>google/gemini-embedding-001 représente le texte par des vecteurs de recherche. Il peut retrouver un passage technique pertinent malgré une question formulée autrement. La route Ailoot annonce 20 000 tokens de contexte hébergé et accepte chaîne, tableau de chaînes ou tableau d’identifiants de tokens, avec un seul type cohérent par requête.</p><p>La réponse contient des vecteurs indexés de nombres flottants finis. Aucune largeur par défaut n’est publiée et la surcharge dimensions est explicitement exclue : établissez la largeur d’index depuis le vecteur retourné et gardez-la fixe. encoding_format accepte float. Aucun sélecteur de tâche ou requête/document n’est exposé. Préparez questions et documents de manière cohérente et conservez modèle exact et largeur ensemble dans l’index.</p>",
      "short_text": "Texte ou identifiants de tokens vers vecteurs float, avec un contexte hébergé annoncé de 20 000 tokens."
    },
    "copy_sha256": "9261996d44957b784368c02fb7325198d9158d2fd0b92c7e262e6e599428c4ca",
    "copy_source": {
      "locale": "fr-be",
      "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7",
      "record_model_id": "google/gemini-embedding-001",
      "source_facts_sha256": "2fd4baee7b3a3f2a29600f7927360e87f060ddaefb156e5bd45613295ca32522",
      "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6"
    },
    "html_sha256": "9b0e691c9b1ca7163c4872d3a477f06f5a46e72753a1e6a2b45f3eb8dc26f39f",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "fr-be",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">G</span><h2 id=\"sheet-title\">Google: Gemini Embedding 001</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Fermer\">×</button></div><div class=\"idline\"><span>Google /</span><code>google/gemini-embedding-001</code><button type=\"button\" id=\"copy-id\">Copier l’ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Rubriques de la fiche modèle\"><button type=\"button\" data-card-jump=\"overview\">Premiers pas</button><button type=\"button\" data-card-jump=\"methods\">Entrées et méthodes</button><button type=\"button\" data-card-jump=\"pricing\">Tarifs</button><button type=\"button\" data-card-jump=\"examples\">Exemples</button><button type=\"button\" data-card-jump=\"results\">Résultats</button><button type=\"button\" data-card-jump=\"aliases\">Alias</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"Méthodes 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|embeddings|/v1/embeddings|google%2Fgemini-embedding-001\">Embeddings</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\">Premiers pas</h3><p class=\"mdesc-full\">Texte ou identifiants de tokens vers vecteurs float, avec un contexte hébergé annoncé de 20 000 tokens.</p><dl class=\"card-io\" data-card-io><div><dt>Entrées acceptées</dt><dd>Texte · token_ids</dd></div><div><dt>Résultats</dt><dd>embedding</dd></div></dl><details class=\"card-about\"><summary>À propos du modèle</summary><p class=\"note-s\" data-model-method-boundary>Cette description présente les capacités du modèle. Les entrées, sorties et options disponibles dans Ailoot pour la méthode sélectionnée figurent ci-dessous.</p><div class=\"mabout\" id=\"m-about\"><p>google/gemini-embedding-001 représente le texte par des vecteurs de recherche. Il peut retrouver un passage technique pertinent malgré une question formulée autrement. La route Ailoot annonce 20 000 tokens de contexte hébergé et accepte chaîne, tableau de chaînes ou tableau d’identifiants de tokens, avec un seul type cohérent par requête.</p><p>La réponse contient des vecteurs indexés de nombres flottants finis. Aucune largeur par défaut n’est publiée et la surcharge dimensions est explicitement exclue : établissez la largeur d’index depuis le vecteur retourné et gardez-la fixe. encoding_format accepte float. Aucun sélecteur de tâche ou requête/document n’est exposé. Préparez questions et documents de manière cohérente et conservez modèle exact et largeur ensemble dans l’index.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Disponible dans Ailoot · entrées et méthodes</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Embeddings</b> <code>POST /v1/embeddings</code></summary><dl class=\"method-capabilities\"><div><dt>Entrée</dt><dd><code>text</code>, <code>token_ids</code></dd></div><div><dt>Sortie</dt><dd><code>embedding</code></dd></div><div><dt>Contexte</dt><dd>20 000 tokens</dd></div><div><dt>Format de sortie</dt><dd>json</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Champ</th><th>Type</th><th>Exigence</th><th>Valeurs et limites</th><th>Par défaut</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Obligatoire</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>google/gemini-embedding-001</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string|string[]|integer[]|integer[][]</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Obligatoire</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>Nombre minimal d’éléments: 1</div><div>Conditions: Lot homogène non vide. Les identifiants de jetons sont des entiers positifs ou nuls.</div><div>Budget d’entrée : Maximum: 20 000 · Unité de texte: octets UTF8 · Unité de tokens: éléments du tableau de tokens</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">encoding_format</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>string</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Facultatif</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>float</div></td><td data-cell-label=\"Par défaut\" data-default=\"known\"><span class=\"card-cell-label\">Par défaut</span>float</td></tr><tr data-parameter-availability=\"unsupported\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">dimensions</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>integer</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Non pris en charge</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>Minimum: 1</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr><tr data-parameter-availability=\"pass_through_metadata\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">user</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>json_value</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Facultatif</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>Conditions: Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr><tr data-parameter-availability=\"pass_through_metadata\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">session_id</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>json_value</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Facultatif</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>Conditions: Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr><tr data-parameter-availability=\"pass_through_metadata\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">trace</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>json_value</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Facultatif</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>Conditions: Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span><code>object</code></td><td data-cell-label=\"Exigence\"><span class=\"card-cell-label\">Exigence</span>Facultatif</td><td data-cell-label=\"Valeurs et limites\"><span class=\"card-cell-label\">Valeurs et limites</span><div>Conditions: provider.options est refusé</div></td><td data-cell-label=\"Par défaut\" data-default=\"unspecified\"><span class=\"card-cell-label\">Par défaut</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Combinaisons d’éléments d’entrée</summary><p class=\"note-s\"><b>text_to_embedding</b></p></details><details class=\"note-s\" data-method-contract><summary>Paramètres et cycle de vie de la méthode</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Paramètre</th><th>Contrat</th></tr></thead><tbody><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>content_type</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>application/json</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>required</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>model, input</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>input_shapes</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>string, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[]</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>encoding_format</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>float</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>dimensions_override</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>false</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>max_input_budget_units</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>20000</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>multimodal_objects</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>false</td></tr><tr><th data-cell-label=\"Paramètre\" scope=\"row\"><span class=\"card-cell-label\">Paramètre</span><code>material_types</code></th><td data-cell-label=\"Contrat\"><span class=\"card-cell-label\">Contrat</span>text, token_ids</td></tr></tbody></table></div><p>Cycle de vie : <code>synchronous_json</code></p><p class=\"note-s\">Conservez tous les indices et toutes les dimensions des vecteurs.</p><p class=\"note-s\">Un nom de modèle multimodal n’autorise pas les objets image sur ce chemin précis.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Tarifs</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Les tarifs n’ajoutent pas d’options de requête. Les paramètres pris en charge figurent dans la méthode sélectionnée.</p><dl data-price-conditions><dt>Mode rapide</dt><dd>Tarif standard <span class=\"note-s\">Lorsque le mode rapide est sélectionné</span></dd><dt>Mode Flex</dt><dd>Tarif standard <span class=\"note-s\">Lorsque le mode flex est sélectionné</span></dd><dt>Effort de raisonnement maximal</dt><dd>Tarif standard <span class=\"note-s\">Lorsque l’effort de raisonnement maximal utilise l’ajustement par défaut (default)</span></dd></dl></div><div data-declared-tariff-pricing><h4>Tarifs Ailoot</h4><h4>Prix par configuration</h4><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Configuration</th><th>Barème tarifaire</th><th>Coût</th></tr></thead><tbody><tr><th data-cell-label=\"Configuration\" scope=\"row\"><span class=\"card-cell-label\">Configuration</span>Tarifs de base des tokens</th><td data-cell-label=\"Barème tarifaire\"><span class=\"card-cell-label\">Barème tarifaire</span>Tarif de base</td><td data-cell-label=\"Coût\"><span class=\"card-cell-label\">Coût</span><div><span>Entrée · Tokens en entrée</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K tokens</span></div><div><span>Sortie · Tokens en sortie</span> <b>$0</b> <span class=\"price-unit\">/ 1K tokens</span></div><div><span>Entrée · Lecture du cache</span> <b>—</b> <span class=\"price-unit\">/ 1K tokens</span></div><div><span>Entrée · Écriture dans le cache</span> <b>—</b> <span class=\"price-unit\">/ 1K tokens</span></div><div><span>Entrée · Écriture dans le cache, 1 h</span> <b>—</b> <span class=\"price-unit\">/ 1K tokens</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot réserve un montant estimé avant une requête. Après le résultat, le montant final est débité selon l’utilisation mesurée. Pour le streaming, le montant final à débiter est calculé à partir du relevé final d’utilisation. <a href=\"/docs/fr-be/billing/reserve/\">Fonctionnement de la réservation et du débit →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Exemples de requêtes</h3><h4>Ailoot Ultra · Embeddings</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Variantes du code\"><button class=\"cg-tab\" id=\"model-code-1486-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1486-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-1486-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1486-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Copier le code\"><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-1486-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-1486-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;google/gemini-embedding-001&quot;, &quot;input&quot;: [&quot;First document&quot;, &quot;Second document&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/embeddings \\\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;data&quot;,[]): print(json.dumps({&quot;index&quot;:x.get(&quot;index&quot;),&quot;embedding&quot;:x.get(&quot;embedding&quot;)}))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-1486-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-1486-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\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.embeddings.create(model=&#39;google/gemini-embedding-001&#39;,input=[&quot;First document&quot;,&quot;Second document&quot;])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Recevoir et enregistrer les résultats</h3><h4>Ailoot Ultra · Embeddings</h4><p class=\"note-s\">json</p><div class=\"card-result-process\" data-all-results><h5>Conserver tous les résultats terminés</h5><p class=\"note-s\">Conservez chaque réponse, fichier et partie de contenu renvoyés dans leur intégralité.</p><p class=\"note-s\">Conservez chaque vecteur avec son indice. Le nombre de vecteurs doit être égal au nombre d’entrées ; les dimensions doivent être cohérentes.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Si la réponse d’origine doit être vérifiée</h5><p class=\"note-s\">Aucun point de terminaison dédié aux tâches d’embedding n’est ajouté.</p></div><details class=\"card-about\" data-output-fields><summary>Champs de la réponse</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Champ</th><th>Type</th></tr></thead><tbody><tr><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">object</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>string</td></tr><tr><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">data[].index</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>integer</td></tr><tr><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">data[].embedding</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>finite float[]</td></tr><tr><th data-cell-label=\"Champ\" scope=\"row\"><span class=\"card-cell-label\">Champ</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Type\" data-field-type><span class=\"card-cell-label\">Type</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Erreurs et étapes suivantes</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Réponse</th><th>Condition</th><th>Étape suivante</th></tr></thead><tbody><tr><th data-cell-label=\"Réponse\" scope=\"row\"><span class=\"card-cell-label\">Réponse</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Condition\"><span class=\"card-cell-label\">Condition</span>Champs obligatoires, représentation des contenus ou valeur de paramètre non valides</td><td data-cell-label=\"Étape suivante\"><span class=\"card-cell-label\">Étape suivante</span>Corrigez les champs indiqués avant une nouvelle requête de création.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Alias</h3><h4>Alias du modèle</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=google%2Fgemini-embedding-001&amp;route=Ultra&amp;caller=google%2Fgemini-embedding-001&amp;fmt=embeddings\"><code>google/gemini-embedding-001</code></a></span></p><h4>Alias des chemins de méthode</h4><p class=\"note-s\">Utilisez les chemins de méthode indiqués ci-dessus.</p><h4>ID d’appel associés</h4><p class=\"note-s\"><a href=\"#m=google%2Fgemini-embedding-001&amp;route=Ultra&amp;caller=google%2Fgemini-embedding-001&amp;fmt=embeddings\"><code>google/gemini-embedding-001</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "google/gemini-embedding-001",
        "fmt": "embeddings",
        "http": "POST",
        "path": "/v1/embeddings",
        "request_model_id": "google/gemini-embedding-001",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|embeddings|/v1/embeddings|google%2Fgemini-embedding-001",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.",
            "errors": [
              {
                "code": null,
                "condition": "Champs obligatoires, représentation des contenus ou valeur de paramètre non valides",
                "http_status": 400,
                "recovery": "Corrigez les champs indiqués avant une nouvelle requête de création.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/embeddings"
              },
              "job_read": null,
              "mode": "synchronous_json",
              "unknown": "Aucun point de terminaison dédié aux tâches d’embedding n’est ajouté."
            },
            "material_combinations": [
              {
                "alternatives": [
                  "string",
                  "string[]",
                  "nonnegative_integer_token_array",
                  "nonnegative_integer_token_array[]"
                ],
                "mode": "text_to_embedding"
              }
            ],
            "operation_modes": [
              "single_embedding",
              "batched_embeddings"
            ],
            "outputs": {
              "all_results": "Conservez chaque vecteur avec son indice. Le nombre de vecteurs doit être égal au nombre d’entrées ; les dimensions doivent être cohérentes.",
              "default_dimensions": null,
              "family": "embedding",
              "fields": [
                {
                  "description": null,
                  "name": "object",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "data[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "data[].embedding",
                  "type": "finite float[]"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "google/gemini-embedding-001"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "budget": {
                  "maximum": 20000,
                  "text_unit": "octets UTF8",
                  "token_unit": "éléments du tableau de tokens"
                },
                "conditions": "Lot homogène non vide. Les identifiants de jetons sont des entiers positifs ou nuls.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "input",
                "required": true,
                "type": "string|string[]|integer[]|integer[][]"
              },
              {
                "availability": "source_interface",
                "default": "float",
                "default_known": true,
                "enum": [
                  "float"
                ],
                "enum_known": true,
                "name": "encoding_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "unsupported",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "dimensions",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "user",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "session_id",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "trace",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "source_interface",
                "conditions": "provider.options est refusé",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "mixed input kinds",
              "empty input",
              "image/audio/file objects",
              "encoding_format=base64",
              "dimensions override"
            ]
          },
          "hints": [
            "Conservez tous les indices et toutes les dimensions des vecteurs.",
            "Un nom de modèle multimodal n’autorise pas les objets image sur ce chemin précis."
          ],
          "input": {
            "content_type": "application/json",
            "dimensions_override": false,
            "encoding_format": [
              "float"
            ],
            "input_shapes": [
              "string",
              "string[]",
              "nonnegative_integer_token_array",
              "nonnegative_integer_token_array[]"
            ],
            "material_types": [
              "text",
              "token_ids"
            ],
            "max_input_budget_units": 20000,
            "multimodal_objects": false,
            "required": [
              "model",
              "input"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_json",
            "unknown": "no embedding job endpoint inferred"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/embeddings"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_to_embedding"
          ],
          "output": {
            "default_dimensions": null,
            "family": "embedding",
            "format": "json",
            "http_success": 200,
            "vectors": "one dense float vector per input; indices/model/usage validated"
          }
        },
        "ctx": 20000,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Tarifs de base des tokens",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "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",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "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"
              }
            ]
          }
        ],
        "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\": \"google/gemini-embedding-001\", \"input\": [\"First document\", \"Second document\"]}')\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/embeddings \\\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(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='google/gemini-embedding-001',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n",
            "label": "Python SDK · all vectors",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "embeddings",
        "hints": [
          "Keep every vector index and dimension.",
          "Multimodal model name does not admit image objects on this exact path."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text",
          "token_ids"
        ],
        "label": "Эмбеддинги",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 0,
        "output": [
          "embedding"
        ],
        "path": "/v1/embeddings",
        "price_conditions": [
          {
            "label": "Mode rapide",
            "value": "Tarif standard",
            "when": "Lorsque le mode rapide est sélectionné"
          },
          {
            "label": "Mode Flex",
            "value": "Tarif standard",
            "when": "Lorsque le mode flex est sélectionné"
          },
          {
            "label": "Effort de raisonnement maximal",
            "value": "Tarif standard",
            "when": "Lorsque l’effort de raisonnement maximal utilise l’ajustement par défaut (default)"
          }
        ],
        "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": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "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",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "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"
              }
            ]
          }
        ],
        "request_model_id": "google/gemini-embedding-001",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "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",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "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"
          }
        ]
      }
    }
  ],
  "model_id": "google/gemini-embedding-001",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "c9e984de9a12cec46ae0a1769d341d7e77cfebd50e2e537b72cfd2405f614a10",
    "input_html_sha256": "ce74f9ae51cdb7080c29c5af56c8c57616a8e0a7a12ef5e79a4eff10ba9e0c58",
    "private_audit_sha256": "9b55cf978b4f2ade49835ea6ba192862c9a927715b6e4eaf263e72c3dd5dbbb8",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/fr-be/google-gemini-embedding-001/",
    "description": "Texte ou identifiants de tokens vers vecteurs float, avec un contexte hébergé annoncé de 20 000 tokens.",
    "locale": "fr-be",
    "md_url": "https://ailoot.ai/models/fr-be/google-gemini-embedding-001/index.md",
    "title": "Google: Gemini Embedding 001 — Ailoot",
    "url": "https://ailoot.ai/models/fr-be/google-gemini-embedding-001/"
  },
  "rawModel": {
    "about": "Gemini Embedding 001 est le modèle de plongement textuel de Google pour représenter des contenus écrits sous forme de vecteurs. Son rôle publié couvre plusieurs domaines, dont la science, les textes juridiques, la finance et la programmation. Le texte constitue l’entrée et les vecteurs de plongement la sortie ; une application de recherche utilise ces vecteurs pour trouver des éléments sources liés.\n\n### Préparer des éléments sources qui restent identifiables\n\nChoisissez un passage ou un élément documentaire contenant les informations que l’utilisateur doit trouver. Préservez son nom de document, son libellé de section et son identifiant source. Un élément de code peut conserver son fichier et l’objectif environnant ; un passage technique peut conserver la terminologie et les unités nécessaires à son interprétation. Ces libellés rendent une correspondance ultérieure utile comme élément à examiner, plutôt que comme un simple score de similarité.\n\nGardez des frontières d’éléments porteuses de sens. Une définition et son explication peuvent aller ensemble, tandis que des sujets sans rapport doivent conserver des identités distinctes. Préservez le texte d’origine avec le vecteur afin qu’un élément retrouvé puisse être examiné ou transmis à une étape ultérieure de génération de réponse.\n\n### Utiliser les vecteurs dans un processus de recherche\n\nGardez la requête et les matériaux indexés dans une configuration de plongement compatible. L’application stocke les vecteurs, les compare et renvoie les éléments sources correspondants. Vérifiez des requêtes représentatives au regard des passages qui doivent être trouvés, en incluant le vocabulaire difficile et différentes manières d’exprimer un même besoin.\n\nUn résultat de recherche utile comprend l’identifiant source et le texte pertinent. Pour une réponse ultérieure, conservez le passage qui étaye chaque constat. Le modèle de plongement fournit la représentation ; une étape distincte de l’application effectue la recherche ou génère une réponse rédigée à partir des éléments retrouvés.\n\n### Capacité d’entrée et continuité de l’index\n\nLe profil hébergé documenté accepte jusqu’à 20 000 tokens par entrée. Divisez les collections plus longues en éléments séparés et étiquetés et préservez leurs relations. Consignez le modèle et la préparation utilisés pour un index, afin de distinguer les changements de configuration du plongement des changements de la collection source.\n\nUn artefact de recherche complet relie la requête aux passages sources sélectionnés et à leurs identifiants. Examinez les correspondances incorrectes ou manquantes au regard du texte réel et des limites des éléments, puis transmettez les éléments pertinents à la tâche qui suit la recherche.",
    "alias_of": null,
    "aliases": [],
    "author": "Google",
    "available": null,
    "canonical_model": "google/gemini-embedding-001",
    "capabilities": {
      "context_length": 20000,
      "manufacturer_input": [
        "text"
      ],
      "manufacturer_output": [
        "embeddings"
      ]
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "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",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "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": "La tarification complète de la configuration figure dans les détails."
      }
    ],
    "ctx": 20000,
    "entity_type": "model",
    "formats": [
      "embeddings"
    ],
    "id": "google/gemini-embedding-001",
    "input": [
      "text",
      "token_ids"
    ],
    "kind": "embedding",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.",
            "errors": [
              {
                "code": null,
                "condition": "Champs obligatoires, représentation des contenus ou valeur de paramètre non valides",
                "http_status": 400,
                "recovery": "Corrigez les champs indiqués avant une nouvelle requête de création.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/embeddings"
              },
              "job_read": null,
              "mode": "synchronous_json",
              "unknown": "Aucun point de terminaison dédié aux tâches d’embedding n’est ajouté."
            },
            "material_combinations": [
              {
                "alternatives": [
                  "string",
                  "string[]",
                  "nonnegative_integer_token_array",
                  "nonnegative_integer_token_array[]"
                ],
                "mode": "text_to_embedding"
              }
            ],
            "operation_modes": [
              "single_embedding",
              "batched_embeddings"
            ],
            "outputs": {
              "all_results": "Conservez chaque vecteur avec son indice. Le nombre de vecteurs doit être égal au nombre d’entrées ; les dimensions doivent être cohérentes.",
              "default_dimensions": null,
              "family": "embedding",
              "fields": [
                {
                  "description": null,
                  "name": "object",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "data[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "data[].embedding",
                  "type": "finite float[]"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "google/gemini-embedding-001"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "budget": {
                  "maximum": 20000,
                  "text_unit": "octets UTF8",
                  "token_unit": "éléments du tableau de tokens"
                },
                "conditions": "Lot homogène non vide. Les identifiants de jetons sont des entiers positifs ou nuls.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "input",
                "required": true,
                "type": "string|string[]|integer[]|integer[][]"
              },
              {
                "availability": "source_interface",
                "default": "float",
                "default_known": true,
                "enum": [
                  "float"
                ],
                "enum_known": true,
                "name": "encoding_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "unsupported",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "dimensions",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "user",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "session_id",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Le code source autorise ce champ de métadonnées JSON ; sa sémantique exacte en amont dépend du modèle.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "trace",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "source_interface",
                "conditions": "provider.options est refusé",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "mixed input kinds",
              "empty input",
              "image/audio/file objects",
              "encoding_format=base64",
              "dimensions override"
            ]
          },
          "hints": [
            "Conservez tous les indices et toutes les dimensions des vecteurs.",
            "Un nom de modèle multimodal n’autorise pas les objets image sur ce chemin précis."
          ],
          "input": {
            "content_type": "application/json",
            "dimensions_override": false,
            "encoding_format": [
              "float"
            ],
            "input_shapes": [
              "string",
              "string[]",
              "nonnegative_integer_token_array",
              "nonnegative_integer_token_array[]"
            ],
            "material_types": [
              "text",
              "token_ids"
            ],
            "max_input_budget_units": 20000,
            "multimodal_objects": false,
            "required": [
              "model",
              "input"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_json",
            "unknown": "no embedding job endpoint inferred"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/embeddings"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_to_embedding"
          ],
          "output": {
            "default_dimensions": null,
            "family": "embedding",
            "format": "json",
            "http_success": 200,
            "vectors": "one dense float vector per input; indices/model/usage validated"
          }
        },
        "ctx": 20000,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Tarifs de base des tokens",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "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",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "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"
              }
            ]
          }
        ],
        "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\": \"google/gemini-embedding-001\", \"input\": [\"First document\", \"Second document\"]}')\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/embeddings \\\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(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='google/gemini-embedding-001',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n",
            "label": "Python SDK · all vectors",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "embeddings",
        "hints": [
          "Keep every vector index and dimension.",
          "Multimodal model name does not admit image objects on this exact path."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text",
          "token_ids"
        ],
        "label": "Эмбеддинги",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 0,
        "output": [
          "embedding"
        ],
        "path": "/v1/embeddings",
        "price_conditions": [
          {
            "label": "Mode rapide",
            "value": "Tarif standard",
            "when": "Lorsque le mode rapide est sélectionné"
          },
          {
            "label": "Mode Flex",
            "value": "Tarif standard",
            "when": "Lorsque le mode flex est sélectionné"
          },
          {
            "label": "Effort de raisonnement maximal",
            "value": "Tarif standard",
            "when": "Lorsque l’effort de raisonnement maximal utilise l’ajustement par défaut (default)"
          }
        ],
        "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": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "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",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "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"
              }
            ]
          }
        ],
        "request_model_id": "google/gemini-embedding-001",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "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",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "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"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "google/gemini-embedding-001",
        "request_model_id": "google/gemini-embedding-001",
        "route_label": "Ultra"
      }
    ],
    "name": "Google: Gemini Embedding 001",
    "price": {
      "in": 0.3,
      "in_label": null,
      "out": 0,
      "out_label": null,
      "scope_label": "Token rates",
      "sort_in": 0.3,
      "sort_out": 0,
      "varies": false
    },
    "pricing_profiles": [
      {
        "dimensions": {
          "regime": "base"
        },
        "label": "Эмбеддинги · Base token rates",
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "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",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "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"
          }
        ]
      }
    ],
    "public_id": "google/gemini-embedding-001",
    "short": "Gemini Embedding 001 est le modèle de plongement textuel de Google pour la recherche dans des domaines tels que la science, les contenus juridiques, la finance et le code. Il convertit le texte en vecteurs, avec une capacité hébergée documentée pouvant atteindre 20 000 tokens par entrée."
  },
  "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": "Texte ou identifiants de tokens vers vecteurs float, avec un contexte hébergé annoncé de 20 000 tokens.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "1aa10137ebeb766375b7c40f2885486fb2fdeff8c3b9b2ca9fffcc77e46d0952",
    "renderer_sha256": "9d578ff8df69ef70403308c9943a1179a11b94114c10b333bf1c012005d4a7f4"
  },
  "sourceRevision": "402db874d9a6e3835eaaab9f3a7da754a61997c28355f963da45c54c267ad373"
}