{ "aboutHtml": "

GLM-4.1V-Thinking-Flash associe la compréhension visuelle à un raisonnement intégré. Zhipu le présente pour interpréter des images et des pages de documents, notamment les graphiques, les problèmes mathématiques, la structure d’interfaces et la localisation visuelle. Il relie ce qui apparaît dans le contenu à une explication de la réponse.

Précisez la question visuelle

Pour un graphique, préservez les libellés d’axes, la légende et les unités, puis indiquez la comparaison ou le calcul. Pour un schéma, fournissez l’énoncé et des annotations lisibles. Pour une interface, identifiez l’objectif de l’utilisateur et les commandes ou la disposition à examiner. Ces détails aident à distinguer une observation visible d’une hypothèse.

Demandez un résultat exploitable

Demandez une interprétation du graphique, une solution détaillée, une description des éléments d’interface pertinents ou un descriptif d’implémentation frontend. Conservez l’image source avec la réponse et vérifiez les libellés, quantités et positions dont dépend le résultat.

Avec Ailoot, utilisez l’identifiant exact du modèle dans /v1/chat/completions et gardez l’image avec sa question dans la conversation. Le contenu visuel utilise image_url ; les sources d’image prises en charge peuvent contenir une adresse d’image ou un URI de données base64. Recueillez la réponse JSON complète ou tous les segments SSE lorsque stream est activé, et conservez usage avec le résultat terminé.

", "aboutText": "GLM-4.1V-Thinking-Flash associe la compréhension visuelle à un raisonnement intégré. Zhipu le présente pour interpréter des images et des pages de documents, notamment les graphiques, les problèmes mathématiques, la structure d’interfaces et la localisation visuelle. Il relie ce qui apparaît dans le contenu à une explication de la réponse.\n\n### Précisez la question visuelle\n\nPour un graphique, préservez les libellés d’axes, la légende et les unités, puis indiquez la comparaison ou le calcul. Pour un schéma, fournissez l’énoncé et des annotations lisibles. Pour une interface, identifiez l’objectif de l’utilisateur et les commandes ou la disposition à examiner. Ces détails aident à distinguer une observation visible d’une hypothèse.\n\n### Demandez un résultat exploitable\n\nDemandez une interprétation du graphique, une solution détaillée, une description des éléments d’interface pertinents ou un descriptif d’implémentation frontend. Conservez l’image source avec la réponse et vérifiez les libellés, quantités et positions dont dépend le résultat.\n\nAvec Ailoot, utilisez l’identifiant exact du modèle dans /v1/chat/completions et gardez l’image avec sa question dans la conversation. Le contenu visuel utilise image_url ; les sources d’image prises en charge peuvent contenir une adresse d’image ou un URI de données base64. Recueillez la réponse JSON complète ou tous les segments SSE lorsque stream est activé, et conservez usage avec le résultat terminé.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "66cee8295c6d47db0c0b7d62987a25fcd588e621b6ef47bbd2ad400f53488047", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "fr", "methods": [ { "html": "
•

glm-4.1v-thinking-flash

Autre /glm-4.1v-thinking-flash

Premiers pas

GLM-4.1V-Thinking-Flash est le modèle de raisonnement visuel de Zhipu pour analyser des graphiques, des schémas scientifiques, des images de documents et des questions d’interface.

Entrées acceptées
Texte · Images
Résultats
Texte
À propos du modèle

Cette description présente les capacités du modèle. Les entrées, sorties et options disponibles dans Ailoot pour la méthode sélectionnée figurent ci-dessous.

GLM-4.1V-Thinking-Flash associe la compréhension visuelle à un raisonnement intégré. Zhipu le présente pour interpréter des images et des pages de documents, notamment les graphiques, les problèmes mathématiques, la structure d’interfaces et la localisation visuelle. Il relie ce qui apparaît dans le contenu à une explication de la réponse.

Précisez la question visuelle

Pour un graphique, préservez les libellés d’axes, la légende et les unités, puis indiquez la comparaison ou le calcul. Pour un schéma, fournissez l’énoncé et des annotations lisibles. Pour une interface, identifiez l’objectif de l’utilisateur et les commandes ou la disposition à examiner. Ces détails aident à distinguer une observation visible d’une hypothèse.

Demandez un résultat exploitable

Demandez une interprétation du graphique, une solution détaillée, une description des éléments d’interface pertinents ou un descriptif d’implémentation frontend. Conservez l’image source avec la réponse et vérifiez les libellés, quantités et positions dont dépend le résultat.

Avec Ailoot, utilisez l’identifiant exact du modèle dans /v1/chat/completions et gardez l’image avec sa question dans la conversation. Le contenu visuel utilise image_url ; les sources d’image prises en charge peuvent contenir une adresse d’image ou un URI de données base64. Recueillez la réponse JSON complète ou tous les segments SSE lorsque stream est activé, et conservez usage avec le résultat terminé.

Disponible dans Ailoot · entrées et méthodes

Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
Types d’entrée
text, image
Types de sortie
text
Format de sortie
JSON or SSE
ChampTypeExigenceValeurs et limitesPar défaut
ChampmodelTypestringExigenceObligatoireValeurs et limites
glm-4.1v-thinking-flash
Conditions: Utilisez exactement ce sélecteur de routage Ailoot.
Par défaut—
ChampmessagesTypearrayExigenceObligatoireValeurs et limites
Conditions:
Par défaut—
ChampstreamTypebooleanExigenceFacultatifValeurs et limites
Conditions:
Par défautfalse
Combinaisons d’éléments d’entrée

text_input · Obligatoire : messages

image_with_text · Obligatoire : messages with actual image content blocks

Paramètres et cycle de vie de la méthode
ParamètreContrat
Paramètrecontent_typeContratapplication/json
ParamètrerequiredContratmodel, messages
ParamètreoptionalContratstream
Paramètrematerial_typesContrattext, image
ParamètreconditionsContratUtilisez exactement ce sélecteur de routage Ailoot., Ce protocole transmet les images lorsque le modèle précis sélectionné prend en charge la vision. L’admission par le protocole ne prouve pas que tous les modèles prennent en charge les images.

Alias de méthode : /chat/completions

Cycle de vie : synchronous_or_streamed

Tarifs

Les tarifs n’ajoutent pas d’options de requête. Les paramètres pris en charge figurent dans la méthode sélectionnée.

Mode rapide
Tarif standard Lorsque le mode rapide est sélectionné
Mode Flex
Tarif standard Lorsque le mode flex est sélectionné
Effort de raisonnement maximal
Tarif standard Lorsque l’effort de raisonnement maximal utilise l’ajustement par défaut (default)
Tarification du cache explicite
Non activé Lorsqu’un cache explicite est demandé
Tarifs nuls pour le texte seul
Le cache, les outils et les médias suivent les conditions tarifaires indiquées séparément pour chacun. Pour des entrées et des sorties exclusivement textuelles

Tarifs Ailoot

Prix par configuration

ConfigurationBarème tarifaireCoût
ConfigurationTarifs de base par jetonBarème tarifaireTarif de baseCoût
Entrée · Tokens en entrée $0 / 1K tokens
Sortie · Tokens en sortie $0 / 1K tokens
Entrée · Lecture du cache $0 / 1K tokens
Entrée · Écriture dans le cache $0 / 1K tokens
Entrée · Écriture dans le cache, 1 h — / 1K tokens

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. Fonctionnement de la réservation et du débit →

Exemples de requêtes

Ailoot Ultra · OpenAI Chat

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('{"model": "glm-4.1v-thinking-flash", "messages": [{"role": "user", "content": "Explain how a rainbow forms."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Recevoir et enregistrer les résultats

Ailoot Ultra · OpenAI Chat

JSON or SSE

Conserver tous les résultats terminés

Conservez chaque réponse, fichier et partie de contenu renvoyés dans leur intégralité.

Conservez chaque bloc de contenu, chaque identifiant d’appel d’outil, la signature de raisonnement lorsqu’elle est renvoyée, tous les deltas SSE et l’intégralité des données de consommation. Le premier fragment de texte ne constitue pas le résultat complet.

Si la réponse d’origine doit être vérifiée

Conservez le X-Client-Request-ID d’origine, la réponse et les en-têtes. Un résultat inconnu ou à l’état result_pending_check n’autorise pas une seconde création.

Champs de la réponse
ChampType
Champchoices[]Typeobject
ChampusageTypeobject
Erreurs et étapes suivantes
RéponseConditionÉtape suivante
Réponse400 · invalid_request_errorConditionUn champ obligatoire, un sélecteur de modèle, un type ou une représentation des données d’entrée est invalide.Étape suivanteExaminez les détails de validation renvoyés avant de préparer une demande distincte.
RéponseConditionLa demande d’origine ou son résultat est inconnu ou nécessite une vérification.Étape suivanteConservez les identifiants et les en-têtes d’origine ; consultez uniquement les enregistrements d’état ou de la bibliothèque pris en charge. Ne renvoyez pas la demande de création.

Alias

Alias du modèle

Ailoot Ultra glm-4.1v-thinking-flash

Alias des chemins de méthode

/chat/completions

ID d’appel associés

glm-4.1v-thinking-flash

", "method_identity": { "effective_request_model_id": "glm-4.1v-thinking-flash", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|glm-4.1v-thinking-flash", "ordinal": 0, "rawMethod": { "available": null, "cache_read": 0, "cache_write": 0, "cache_write_1h": null, "contract": { "data": { "accepted_material_guidance": { "content_type": "application/json", "example_scope": "The preserved text example is one valid request form, not the full protocol input set.", "image_condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "material_types": [ "text", "image" ], "text_file_material": "Actual UTF-8 text can be inserted in a text content part." }, "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "errors": [ { "condition": "Un champ obligatoire, un sélecteur de modèle, un type ou une représentation des données d’entrée est invalide.", "http_status": 400, "recovery": "Examinez les détails de validation renvoyés avant de préparer une demande distincte.", "type": "invalid_request_error" }, { "condition": "La demande d’origine ou son résultat est inconnu ou nécessite une vérification.", "http_status": null, "recovery": "Conservez les identifiants et les en-têtes d’origine ; consultez uniquement les enregistrements d’état ou de la bibliothèque pris en charge. Ne renvoyez pas la demande de création.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Conservez le X-Client-Request-ID d’origine, la réponse et les en-têtes. Un résultat inconnu ou à l’état result_pending_check n’autorise pas une seconde création.", "unknown_no_replay": true }, "material_combinations": [ { "materials": [ "text" ], "mode": "text_input", "required": [ "messages" ] }, { "condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "materials": [ "text", "image" ], "mode": "image_with_text", "required": [ "messages with actual image content blocks" ] } ], "model_capability_scope": { "all_models_vision_claim": false, "manufacturer_description_preserved": "Retain grounded accepted legacy vision descriptions; a plain text example is not a capability ceiling.", "model_vision": "conditional_on_exact_model_capability", "transport_materials": [ "text", "image" ], "video_audio_inferred": false }, "outputs": { "all_results": "Conservez chaque bloc de contenu, chaque identifiant d’appel d’outil, la signature de raisonnement lorsqu’elle est renvoyée, tous les deltas SSE et l’intégralité des données de consommation. Le premier fragment de texte ne constitue pas le résultat complet.", "every_actual_output": true, "family": "text", "fields": [ { "name": "choices[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" }, "parameters": [ { "conditions": "Utilisez exactement ce sélecteur de routage Ailoot.", "default_known": false, "enum": [ "glm-4.1v-thinking-flash" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "image_url": { "properties": { "detail": { "type": "string" }, "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "conditions": "", "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "request_schema": { "additionalProperties": true, "properties": { "messages": { "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "image_url": { "properties": { "detail": { "type": "string" }, "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "glm-4.1v-thinking-flash" ], "type": "string" }, "stream": { "default": false, "type": "boolean" } }, "required": [ "model", "messages" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": false, "body": { "messages": [ { "content": "Explain how a rainbow forms.", "role": "user" } ], "model": "glm-4.1v-thinking-flash" }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Utilisez exactement ce sélecteur de routage Ailoot.", "Ce protocole transmet les images lorsque le modèle précis sélectionné prend en charge la vision. L’admission par le protocole ne prouve pas que tous les modèles prennent en charge les images." ], "content_type": "application/json", "material_types": [ "text", "image" ], "optional": [ "stream" ], "required": [ "model", "messages" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [ "/chat/completions" ], "output": { "all_results": "Retain every content block, tool-call ID, thinking signature when returned, all SSE deltas and complete usage. A first text fragment is not the whole result.", "every_actual_output": true, "family": "text", "fields": [ { "name": "choices[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.1v-thinking-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain how a rainbow forms.\"}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\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": 1, "flex_multiplier": 1, "fmt": "chat", "http": "POST", "in": 0, "input": [ "text", "image" ], "input_conditions": { "image": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model." }, "label": "OpenAI Chat", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [ "/chat/completions" ], "out": 0, "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Tarifs nuls pour le texte seul", "value": "Le cache, les outils et les médias suivent les conditions tarifaires indiquées séparément pour chacun.", "when": "Pour des entrées et des sorties exclusivement textuelles" } ], "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", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } }, { "html": "
•

glm-4.1v-thinking-flash

Autre /glm-4.1v-thinking-flash

Premiers pas

GLM-4.1V-Thinking-Flash est le modèle de raisonnement visuel de Zhipu pour analyser des graphiques, des schémas scientifiques, des images de documents et des questions d’interface.

Entrées acceptées
Texte · Images
Résultats
json · sse
À propos du modèle

Cette description présente les capacités du modèle. Les entrées, sorties et options disponibles dans Ailoot pour la méthode sélectionnée figurent ci-dessous.

GLM-4.1V-Thinking-Flash associe la compréhension visuelle à un raisonnement intégré. Zhipu le présente pour interpréter des images et des pages de documents, notamment les graphiques, les problèmes mathématiques, la structure d’interfaces et la localisation visuelle. Il relie ce qui apparaît dans le contenu à une explication de la réponse.

Précisez la question visuelle

Pour un graphique, préservez les libellés d’axes, la légende et les unités, puis indiquez la comparaison ou le calcul. Pour un schéma, fournissez l’énoncé et des annotations lisibles. Pour une interface, identifiez l’objectif de l’utilisateur et les commandes ou la disposition à examiner. Ces détails aident à distinguer une observation visible d’une hypothèse.

Demandez un résultat exploitable

Demandez une interprétation du graphique, une solution détaillée, une description des éléments d’interface pertinents ou un descriptif d’implémentation frontend. Conservez l’image source avec la réponse et vérifiez les libellés, quantités et positions dont dépend le résultat.

Avec Ailoot, utilisez l’identifiant exact du modèle dans /v1/chat/completions et gardez l’image avec sa question dans la conversation. Le contenu visuel utilise image_url ; les sources d’image prises en charge peuvent contenir une adresse d’image ou un URI de données base64. Recueillez la réponse JSON complète ou tous les segments SSE lorsque stream est activé, et conservez usage avec le résultat terminé.

Disponible dans Ailoot · entrées et méthodes

Ailoot Ultra · Anthropic Messages POST /v1/messages
Types d’entrée
text, image
Types de sortie
json, sse
Format de sortie
JSON or SSE
ChampTypeExigenceValeurs et limitesPar défaut
ChampmodelTypestringExigenceObligatoireValeurs et limites
glm-4.1v-thinking-flash
Conditions: Utilisez exactement ce sélecteur de routage Ailoot.
Par défaut—
ChampmessagesTypearrayExigenceObligatoireValeurs et limites
Conditions:
Par défaut—
ChampstreamTypebooleanExigenceFacultatifValeurs et limites
Conditions:
Par défautfalse
Champmax_tokensTypeintegerExigenceObligatoireValeurs et limites
Minimum: 1
Conditions:
Par défaut—
Combinaisons d’éléments d’entrée

text_input · Obligatoire : messages

image_with_text · Obligatoire : messages with actual image content blocks

Paramètres et cycle de vie de la méthode
ParamètreContrat
Paramètrecontent_typeContratapplication/json
ParamètrerequiredContratmodel, messages, max_tokens
ParamètreoptionalContratstream
Paramètrematerial_typesContrattext, image
ParamètreconditionsContratUtilisez exactement ce sélecteur de routage Ailoot., Ce protocole transmet les images lorsque le modèle précis sélectionné prend en charge la vision. L’admission par le protocole ne prouve pas que tous les modèles prennent en charge les images.

Cycle de vie : synchronous_or_streamed

Tarifs

Les tarifs n’ajoutent pas d’options de requête. Les paramètres pris en charge figurent dans la méthode sélectionnée.

Mode rapide
Tarif standard Lorsque le mode rapide est sélectionné
Mode Flex
Tarif standard Lorsque le mode flex est sélectionné
Effort de raisonnement maximal
Tarif standard Lorsque l’effort de raisonnement maximal utilise l’ajustement par défaut (default)
Tarification du cache explicite
Non activé Lorsqu’un cache explicite est demandé
Tarifs nuls pour le texte seul
Le cache, les outils et les médias suivent les conditions tarifaires indiquées séparément pour chacun. Pour des entrées et des sorties exclusivement textuelles

Tarifs Ailoot

Prix par configuration

ConfigurationBarème tarifaireCoût
ConfigurationTarifs de base par jetonBarème tarifaireTarif de baseCoût
Entrée · Tokens en entrée $0 / 1K tokens
Sortie · Tokens en sortie $0 / 1K tokens
Entrée · Lecture du cache $0 / 1K tokens
Entrée · Écriture dans le cache $0 / 1K tokens
Entrée · Écriture dans le cache, 1 h — / 1K tokens

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. Fonctionnement de la réservation et du débit →

Exemples de requêtes

Ailoot Ultra · Anthropic Messages

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('{"model": "glm-4.1v-thinking-flash", "messages": [{"role": "user", "content": "Explain how a rainbow forms."}], "max_tokens": 256}')\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/messages \\\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

Recevoir et enregistrer les résultats

Ailoot Ultra · Anthropic Messages

JSON or SSE

Conserver tous les résultats terminés

Conservez chaque réponse, fichier et partie de contenu renvoyés dans leur intégralité.

Conservez chaque bloc de contenu, chaque identifiant d’appel d’outil, la signature de raisonnement lorsqu’elle est renvoyée, tous les deltas SSE et l’intégralité des données de consommation. Le premier fragment de texte ne constitue pas le résultat complet.

Si la réponse d’origine doit être vérifiée

Conservez le X-Client-Request-ID d’origine, la réponse et les en-têtes. Un résultat inconnu ou à l’état result_pending_check n’autorise pas une seconde création.

Champs de la réponse
ChampType
Champcontent[]Typeobject
ChampusageTypeobject
Erreurs et étapes suivantes
RéponseConditionÉtape suivante
Réponse400 · invalid_request_errorConditionUn champ obligatoire, un sélecteur de modèle, un type ou une représentation des données d’entrée est invalide.Étape suivanteExaminez les détails de validation renvoyés avant de préparer une demande distincte.
RéponseConditionLa demande d’origine ou son résultat est inconnu ou nécessite une vérification.Étape suivanteConservez les identifiants et les en-têtes d’origine ; consultez uniquement les enregistrements d’état ou de la bibliothèque pris en charge. Ne renvoyez pas la demande de création.

Alias

Alias du modèle

Ailoot Ultra glm-4.1v-thinking-flash

Alias des chemins de méthode

/chat/completions

ID d’appel associés

glm-4.1v-thinking-flash

", "method_identity": { "effective_request_model_id": "glm-4.1v-thinking-flash", "fmt": "messages", "http": "POST", "path": "/v1/messages", "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra" }, "method_key": "Ultra|messages|/v1/messages|glm-4.1v-thinking-flash", "ordinal": 1, "rawMethod": { "available": null, "cache_read": 0, "cache_write": 0, "cache_write_1h": null, "contract": { "data": { "accepted_material_guidance": { "content_type": "application/json", "example_scope": "The preserved text example is one valid request form, not the full protocol input set.", "image_condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "material_types": [ "text", "image" ], "text_file_material": "Actual UTF-8 text can be inserted in a text content part." }, "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "errors": [ { "condition": "Un champ obligatoire, un sélecteur de modèle, un type ou une représentation des données d’entrée est invalide.", "http_status": 400, "recovery": "Examinez les détails de validation renvoyés avant de préparer une demande distincte.", "type": "invalid_request_error" }, { "condition": "La demande d’origine ou son résultat est inconnu ou nécessite une vérification.", "http_status": null, "recovery": "Conservez les identifiants et les en-têtes d’origine ; consultez uniquement les enregistrements d’état ou de la bibliothèque pris en charge. Ne renvoyez pas la demande de création.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Conservez le X-Client-Request-ID d’origine, la réponse et les en-têtes. Un résultat inconnu ou à l’état result_pending_check n’autorise pas une seconde création.", "unknown_no_replay": true }, "material_combinations": [ { "materials": [ "text" ], "mode": "text_input", "required": [ "messages" ] }, { "condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "materials": [ "text", "image" ], "mode": "image_with_text", "required": [ "messages with actual image content blocks" ] } ], "model_capability_scope": { "all_models_vision_claim": false, "manufacturer_description_preserved": "Retain grounded accepted legacy vision descriptions; a plain text example is not a capability ceiling.", "model_vision": "conditional_on_exact_model_capability", "transport_materials": [ "text", "image" ], "video_audio_inferred": false }, "outputs": { "all_results": "Conservez chaque bloc de contenu, chaque identifiant d’appel d’outil, la signature de raisonnement lorsqu’elle est renvoyée, tous les deltas SSE et l’intégralité des données de consommation. Le premier fragment de texte ne constitue pas le résultat complet.", "every_actual_output": true, "family": "text", "fields": [ { "name": "content[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" }, "parameters": [ { "conditions": "Utilisez exactement ce sélecteur de routage Ailoot.", "default_known": false, "enum": [ "glm-4.1v-thinking-flash" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "source": { "oneOf": [ { "properties": { "type": { "const": "url" }, "url": { "type": "string" } }, "required": [ "type", "url" ], "type": "object" }, { "properties": { "data": { "type": "string" }, "media_type": { "type": "string" }, "type": { "const": "base64" } }, "required": [ "type", "media_type", "data" ], "type": "object" } ] }, "type": { "const": "image" } }, "required": [ "type", "source" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "conditions": "", "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" }, { "conditions": "", "default_known": false, "enum_known": false, "minimum": 1, "name": "max_tokens", "required": true, "type": "integer" } ], "request_schema": { "additionalProperties": true, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "source": { "oneOf": [ { "properties": { "type": { "const": "url" }, "url": { "type": "string" } }, "required": [ "type", "url" ], "type": "object" }, { "properties": { "data": { "type": "string" }, "media_type": { "type": "string" }, "type": { "const": "base64" } }, "required": [ "type", "media_type", "data" ], "type": "object" } ] }, "type": { "const": "image" } }, "required": [ "type", "source" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "glm-4.1v-thinking-flash" ], "type": "string" }, "stream": { "default": false, "type": "boolean" } }, "required": [ "model", "messages", "max_tokens" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": false, "body": { "max_tokens": 256, "messages": [ { "content": "Explain how a rainbow forms.", "role": "user" } ], "model": "glm-4.1v-thinking-flash" }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Utilisez exactement ce sélecteur de routage Ailoot.", "Ce protocole transmet les images lorsque le modèle précis sélectionné prend en charge la vision. L’admission par le protocole ne prouve pas que tous les modèles prennent en charge les images." ], "content_type": "application/json", "material_types": [ "text", "image" ], "optional": [ "stream" ], "required": [ "model", "messages", "max_tokens" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/messages" }, "method_aliases": [], "output": { "all_results": "Retain every content block, tool-call ID, thinking signature when returned, all SSE deltas and complete usage. A first text fragment is not the whole result.", "every_actual_output": true, "family": "text", "fields": [ { "name": "content[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.1v-thinking-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain how a rainbow forms.\"}], \"max_tokens\": 256}')\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/messages \\\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": "anthropic", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "messages", "http": "POST", "in": 0, "input": [ "text", "image" ], "input_conditions": { "image": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model." }, "label": "Anthropic Messages", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": 0, "output": [ "json", "sse" ], "path": "/v1/messages", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Tarifs nuls pour le texte seul", "value": "Le cache, les outils et les médias suivent les conditions tarifaires indiquées séparément pour chacun.", "when": "Pour des entrées et des sorties exclusivement textuelles" } ], "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", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } } ], "model_id": "glm-4.1v-thinking-flash", "nativeProvenance": { "input_facts_canonical_sha256": "c0fb3e6f5e2e36aa3d08e65f30841873c0a245677443ec93e76b3357bc1206a8", "input_html_sha256": "91f8460cdc226dfed04da7a699bab93dadb6c7beb762189a1e4ea795a4ef1e66", "private_audit_sha256": "7afc36e0d98ba42d902722994909f6788a0989ab9bd258a93a6cd6027be39b40", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/fr/glm-4-1v-thinking-flash/", "description": "GLM-4.1V-Thinking-Flash est le modèle de raisonnement visuel de Zhipu pour analyser des graphiques, des schémas scientifiques, des images de documents et des questions d’interface.", "locale": "fr", "md_url": "https://ailoot.ai/models/fr/glm-4-1v-thinking-flash/index.md", "title": "glm-4.1v-thinking-flash — Ailoot", "url": "https://ailoot.ai/models/fr/glm-4-1v-thinking-flash/" }, "rawModel": { "about": "GLM-4.1V-Thinking-Flash associe la compréhension visuelle à un raisonnement intégré. Zhipu le présente pour interpréter des images et des pages de documents, notamment les graphiques, les problèmes mathématiques, la structure d’interfaces et la localisation visuelle. Il relie ce qui apparaît dans le contenu à une explication de la réponse.\n\n### Précisez la question visuelle\n\nPour un graphique, préservez les libellés d’axes, la légende et les unités, puis indiquez la comparaison ou le calcul. Pour un schéma, fournissez l’énoncé et des annotations lisibles. Pour une interface, identifiez l’objectif de l’utilisateur et les commandes ou la disposition à examiner. Ces détails aident à distinguer une observation visible d’une hypothèse.\n\n### Demandez un résultat exploitable\n\nDemandez une interprétation du graphique, une solution détaillée, une description des éléments d’interface pertinents ou un descriptif d’implémentation frontend. Conservez l’image source avec la réponse et vérifiez les libellés, quantités et positions dont dépend le résultat.\n\nAvec Ailoot, utilisez l’identifiant exact du modèle dans /v1/chat/completions et gardez l’image avec sa question dans la conversation. Le contenu visuel utilise image_url ; les sources d’image prises en charge peuvent contenir une adresse d’image ou un URI de données base64. Recueillez la réponse JSON complète ou tous les segments SSE lorsque stream est activé, et conservez usage avec le résultat terminé.", "alias_of": null, "aliases": [], "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": null, "formats": [ "chat", "messages" ], "id": "glm-4.1v-thinking-flash", "input": [ "text", "image" ], "kind": "text", "max_out": null, "methods": [ { "available": null, "cache_read": 0, "cache_write": 0, "cache_write_1h": null, "contract": { "data": { "accepted_material_guidance": { "content_type": "application/json", "example_scope": "The preserved text example is one valid request form, not the full protocol input set.", "image_condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "material_types": [ "text", "image" ], "text_file_material": "Actual UTF-8 text can be inserted in a text content part." }, "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "errors": [ { "condition": "Un champ obligatoire, un sélecteur de modèle, un type ou une représentation des données d’entrée est invalide.", "http_status": 400, "recovery": "Examinez les détails de validation renvoyés avant de préparer une demande distincte.", "type": "invalid_request_error" }, { "condition": "La demande d’origine ou son résultat est inconnu ou nécessite une vérification.", "http_status": null, "recovery": "Conservez les identifiants et les en-têtes d’origine ; consultez uniquement les enregistrements d’état ou de la bibliothèque pris en charge. Ne renvoyez pas la demande de création.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Conservez le X-Client-Request-ID d’origine, la réponse et les en-têtes. Un résultat inconnu ou à l’état result_pending_check n’autorise pas une seconde création.", "unknown_no_replay": true }, "material_combinations": [ { "materials": [ "text" ], "mode": "text_input", "required": [ "messages" ] }, { "condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "materials": [ "text", "image" ], "mode": "image_with_text", "required": [ "messages with actual image content blocks" ] } ], "model_capability_scope": { "all_models_vision_claim": false, "manufacturer_description_preserved": "Retain grounded accepted legacy vision descriptions; a plain text example is not a capability ceiling.", "model_vision": "conditional_on_exact_model_capability", "transport_materials": [ "text", "image" ], "video_audio_inferred": false }, "outputs": { "all_results": "Conservez chaque bloc de contenu, chaque identifiant d’appel d’outil, la signature de raisonnement lorsqu’elle est renvoyée, tous les deltas SSE et l’intégralité des données de consommation. Le premier fragment de texte ne constitue pas le résultat complet.", "every_actual_output": true, "family": "text", "fields": [ { "name": "choices[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" }, "parameters": [ { "conditions": "Utilisez exactement ce sélecteur de routage Ailoot.", "default_known": false, "enum": [ "glm-4.1v-thinking-flash" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "image_url": { "properties": { "detail": { "type": "string" }, "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "conditions": "", "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "request_schema": { "additionalProperties": true, "properties": { "messages": { "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "image_url": { "properties": { "detail": { "type": "string" }, "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "glm-4.1v-thinking-flash" ], "type": "string" }, "stream": { "default": false, "type": "boolean" } }, "required": [ "model", "messages" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": false, "body": { "messages": [ { "content": "Explain how a rainbow forms.", "role": "user" } ], "model": "glm-4.1v-thinking-flash" }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Utilisez exactement ce sélecteur de routage Ailoot.", "Ce protocole transmet les images lorsque le modèle précis sélectionné prend en charge la vision. L’admission par le protocole ne prouve pas que tous les modèles prennent en charge les images." ], "content_type": "application/json", "material_types": [ "text", "image" ], "optional": [ "stream" ], "required": [ "model", "messages" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [ "/chat/completions" ], "output": { "all_results": "Retain every content block, tool-call ID, thinking signature when returned, all SSE deltas and complete usage. A first text fragment is not the whole result.", "every_actual_output": true, "family": "text", "fields": [ { "name": "choices[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.1v-thinking-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain how a rainbow forms.\"}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\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": 1, "flex_multiplier": 1, "fmt": "chat", "http": "POST", "in": 0, "input": [ "text", "image" ], "input_conditions": { "image": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model." }, "label": "OpenAI Chat", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [ "/chat/completions" ], "out": 0, "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Tarifs nuls pour le texte seul", "value": "Le cache, les outils et les médias suivent les conditions tarifaires indiquées séparément pour chacun.", "when": "Pour des entrées et des sorties exclusivement textuelles" } ], "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", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "available": null, "cache_read": 0, "cache_write": 0, "cache_write_1h": null, "contract": { "data": { "accepted_material_guidance": { "content_type": "application/json", "example_scope": "The preserved text example is one valid request form, not the full protocol input set.", "image_condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "material_types": [ "text", "image" ], "text_file_material": "Actual UTF-8 text can be inserted in a text content part." }, "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "errors": [ { "condition": "Un champ obligatoire, un sélecteur de modèle, un type ou une représentation des données d’entrée est invalide.", "http_status": 400, "recovery": "Examinez les détails de validation renvoyés avant de préparer une demande distincte.", "type": "invalid_request_error" }, { "condition": "La demande d’origine ou son résultat est inconnu ou nécessite une vérification.", "http_status": null, "recovery": "Conservez les identifiants et les en-têtes d’origine ; consultez uniquement les enregistrements d’état ou de la bibliothèque pris en charge. Ne renvoyez pas la demande de création.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Conservez le X-Client-Request-ID d’origine, la réponse et les en-têtes. Un résultat inconnu ou à l’état result_pending_check n’autorise pas une seconde création.", "unknown_no_replay": true }, "material_combinations": [ { "materials": [ "text" ], "mode": "text_input", "required": [ "messages" ] }, { "condition": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model.", "materials": [ "text", "image" ], "mode": "image_with_text", "required": [ "messages with actual image content blocks" ] } ], "model_capability_scope": { "all_models_vision_claim": false, "manufacturer_description_preserved": "Retain grounded accepted legacy vision descriptions; a plain text example is not a capability ceiling.", "model_vision": "conditional_on_exact_model_capability", "transport_materials": [ "text", "image" ], "video_audio_inferred": false }, "outputs": { "all_results": "Conservez chaque bloc de contenu, chaque identifiant d’appel d’outil, la signature de raisonnement lorsqu’elle est renvoyée, tous les deltas SSE et l’intégralité des données de consommation. Le premier fragment de texte ne constitue pas le résultat complet.", "every_actual_output": true, "family": "text", "fields": [ { "name": "content[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" }, "parameters": [ { "conditions": "Utilisez exactement ce sélecteur de routage Ailoot.", "default_known": false, "enum": [ "glm-4.1v-thinking-flash" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "source": { "oneOf": [ { "properties": { "type": { "const": "url" }, "url": { "type": "string" } }, "required": [ "type", "url" ], "type": "object" }, { "properties": { "data": { "type": "string" }, "media_type": { "type": "string" }, "type": { "const": "base64" } }, "required": [ "type", "media_type", "data" ], "type": "object" } ] }, "type": { "const": "image" } }, "required": [ "type", "source" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "conditions": "", "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" }, { "conditions": "", "default_known": false, "enum_known": false, "minimum": 1, "name": "max_tokens", "required": true, "type": "integer" } ], "request_schema": { "additionalProperties": true, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "source": { "oneOf": [ { "properties": { "type": { "const": "url" }, "url": { "type": "string" } }, "required": [ "type", "url" ], "type": "object" }, { "properties": { "data": { "type": "string" }, "media_type": { "type": "string" }, "type": { "const": "base64" } }, "required": [ "type", "media_type", "data" ], "type": "object" } ] }, "type": { "const": "image" } }, "required": [ "type", "source" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "glm-4.1v-thinking-flash" ], "type": "string" }, "stream": { "default": false, "type": "boolean" } }, "required": [ "model", "messages", "max_tokens" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": false, "body": { "max_tokens": 256, "messages": [ { "content": "Explain how a rainbow forms.", "role": "user" } ], "model": "glm-4.1v-thinking-flash" }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Utilisez exactement ce sélecteur de routage Ailoot.", "Ce protocole transmet les images lorsque le modèle précis sélectionné prend en charge la vision. L’admission par le protocole ne prouve pas que tous les modèles prennent en charge les images." ], "content_type": "application/json", "material_types": [ "text", "image" ], "optional": [ "stream" ], "required": [ "model", "messages", "max_tokens" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/messages" }, "method_aliases": [], "output": { "all_results": "Retain every content block, tool-call ID, thinking signature when returned, all SSE deltas and complete usage. A first text fragment is not the whole result.", "every_actual_output": true, "family": "text", "fields": [ { "name": "content[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.1v-thinking-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain how a rainbow forms.\"}], \"max_tokens\": 256}')\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/messages \\\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": "anthropic", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "messages", "http": "POST", "in": 0, "input": [ "text", "image" ], "input_conditions": { "image": "Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model." }, "label": "Anthropic Messages", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": 0, "output": [ "json", "sse" ], "path": "/v1/messages", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Tarifs nuls pour le texte seul", "value": "Le cache, les outils et les médias suivent les conditions tarifaires indiquées séparément pour chacun.", "when": "Pour des entrées et des sorties exclusivement textuelles" } ], "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", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "model_aliases": [ { "canonical_model_id": "glm-4.1v-thinking-flash", "request_model_id": "glm-4.1v-thinking-flash", "route_label": "Ultra" } ], "name": "glm-4.1v-thinking-flash", "price": { "in": 0, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0, "sort_out": 0, "varies": false }, "short": "GLM-4.1V-Thinking-Flash est le modèle de raisonnement visuel de Zhipu pour analyser des graphiques, des schémas scientifiques, des images de documents et des questions d’interface.", "title": "glm-4.1v-thinking-flash" }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 }, { "contract_json_pointer": "/methods/1/rawMethod/contract", "html_json_pointer": "/methods/1/html", "method_ordinal": 1 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod", "/methods/1/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "GLM-4.1V-Thinking-Flash est le modèle de raisonnement visuel de Zhipu pour analyser des graphiques, des schémas scientifiques, des images de documents et des questions d’interface.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "4257f524959b4d34e4fa00bd172a0ca275e2f33456dfb77b58bc40547a8089cf", "renderer_sha256": "44d2db1deadc475e1793597083716540bae7bbc53606f05f58780fec5f115dd4" }, "sourceRevision": "5ab8cf4db777274b5c85c978d9c1725c5b94e0b3becd8d55db2a435d2d64ab1a" }