{ "aboutHtml": "

THUDM/GLM-4.1V-9B-Thinking recibe imágenes junto con texto y devuelve texto. Una tarea práctica es aportar un diagrama y pedir explicar la conexión entre dos componentes etiquetados, señalando expresamente las etiquetas dudosas. Su entrada visual lo diferencia de perfiles GLM que solo declaran texto en Ailoot.

El método es /v1/chat/completions con model, messages y stream opcional. No se expone presupuesto de razonamiento ni cuota numérica de contexto o salida. Thinking pertenece al identificador exacto, sin añadir controles de solicitud. Devuelve una interpretación escrita, no un diagrama editado ni una imagen nueva.

", "aboutText": "THUDM/GLM-4.1V-9B-Thinking recibe imágenes junto con texto y devuelve texto. Una tarea práctica es aportar un diagrama y pedir explicar la conexión entre dos componentes etiquetados, señalando expresamente las etiquetas dudosas. Su entrada visual lo diferencia de perfiles GLM que solo declaran texto en Ailoot. El método es /v1/chat/completions con model, messages y stream opcional. No se expone presupuesto de razonamiento ni cuota numérica de contexto o salida. Thinking pertenece al identificador exacto, sin añadir controles de solicitud. Devuelve una interpretación escrita, no un diagrama editado ni una imagen nueva.", "editorialOverlay": { "copy_fields": { "about_html": "

THUDM/GLM-4.1V-9B-Thinking recibe imágenes junto con texto y devuelve texto. Una tarea práctica es aportar un diagrama y pedir explicar la conexión entre dos componentes etiquetados, señalando expresamente las etiquetas dudosas. Su entrada visual lo diferencia de perfiles GLM que solo declaran texto en Ailoot.

El método es /v1/chat/completions con model, messages y stream opcional. No se expone presupuesto de razonamiento ni cuota numérica de contexto o salida. Thinking pertenece al identificador exacto, sin añadir controles de solicitud. Devuelve una interpretación escrita, no un diagrama editado ni una imagen nueva.

", "short_text": "Chat GLM de texto e imágenes para preguntas visuales que requieren respuesta escrita." }, "copy_sha256": "54bc3632e7b83b8c26433ee1b76776be875c737dbbedf34a9dcee148a128e804", "copy_source": { "locale": "es", "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7", "record_model_id": "THUDM/GLM-4.1V-9B-Thinking", "source_facts_sha256": "f8e0274eb3d149d44fece555ac5a67f8abfc9c595c68d73ffc9cbe88c47cbc99", "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6" }, "html_sha256": "d8ae7a5e870f381461372374546eebc3c0d3353a7413f78c4c56d27ed49d1d92", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "es", "methods": [ { "html": "
•

THUDM/GLM-4.1V-9B-Thinking

Otros /THUDM/GLM-4.1V-9B-Thinking

Primeros pasos

Chat GLM de texto e imágenes para preguntas visuales que requieren respuesta escrita.

Entradas aceptadas
Texto · Imágenes
Resultados
Texto
Sobre el modelo

Esta descripción cubre las capacidades del modelo. Las entradas, salidas y opciones disponibles en Ailoot se indican a continuación para el método seleccionado.

THUDM/GLM-4.1V-9B-Thinking recibe imágenes junto con texto y devuelve texto. Una tarea práctica es aportar un diagrama y pedir explicar la conexión entre dos componentes etiquetados, señalando expresamente las etiquetas dudosas. Su entrada visual lo diferencia de perfiles GLM que solo declaran texto en Ailoot.

El método es /v1/chat/completions con model, messages y stream opcional. No se expone presupuesto de razonamiento ni cuota numérica de contexto o salida. Thinking pertenece al identificador exacto, sin añadir controles de solicitud. Devuelve una interpretación escrita, no un diagrama editado ni una imagen nueva.

Disponible en Ailoot · entradas y métodos

Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
Tipos de entrada
text, image
Tipos de salida
text
Formato de salida
JSON or SSE
CampoTipoRequisitoValores y límitesPredeterminado
CampomodelTipostringRequisitoObligatorioValores y límites
THUDM/GLM-4.1V-9B-Thinking
Condiciones: Usa exactamente este selector de enrutamiento de Ailoot.
Predeterminado—
CampomessagesTipoarrayRequisitoObligatorioValores y límites
Condiciones:
Predeterminado—
CampostreamTipobooleanRequisitoOpcionalValores y límites
Condiciones:
Predeterminadofalse
Combinaciones de materiales de entrada

text_input · Obligatorio: messages

image_with_text · Obligatorio: messages with actual image content blocks

Parámetros del método y ciclo de vida
ParámetroContrato
Parámetrocontent_typeContratoapplication/json
ParámetrorequiredContratomodel, messages
ParámetrooptionalContratostream
Parámetromaterial_typesContratotext, image
ParámetroconditionsContratoUsa exactamente este selector de enrutamiento de Ailoot., Este protocolo transporta contenido de imagen cuando el modelo concreto seleccionado admite visión. Que el protocolo admita la solicitud no demuestra que todos los modelos puedan procesar imágenes.

Alias de método: /chat/completions

Ciclo de vida: synchronous_or_streamed

Planes

Las referencias tarifarias no añaden opciones a la solicitud. Los parámetros admitidos se indican en el método seleccionado.

Modo rápido
Tarifa estándar Cuando se selecciona el modo rápido
Modo flex
Tarifa estándar Cuando se selecciona el modo flex
Esfuerzo máximo de razonamiento
Tarifa estándar Cuando el esfuerzo máximo de razonamiento utiliza el ajuste predeterminado (default)
Precios de caché explícita
No habilitado Cuando se solicita caché explícita
Tarifas cero solo para texto
La caché, las herramientas y el contenido multimedia siguen sus respectivas condiciones de precio, indicadas por separado. Para entrada y salida de texto únicamente

Tarifas de Ailoot

Precios por configuración

ConfiguraciónTabla de tarifasCargo
ConfiguraciónTarifas base por tokenTabla de tarifasTarifa baseCargo
Entrada · Tokens de entrada $0 / 1K tokens
Salida · Tokens de salida $0 / 1K tokens
Entrada · Lectura de caché $0 / 1K tokens
Entrada · Escritura en caché $0 / 1K tokens
Entrada · Escritura en caché, 1 hora — / 1K tokens

Ailoot reserva un importe estimado antes de la solicitud. Tras obtener el resultado, liquida el cargo definitivo según el uso medido. En las respuestas en flujo, la liquidación usa el registro de uso final. Cómo funcionan la reserva y la liquidación →

Solicitudes de ejemplo

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": "THUDM/GLM-4.1V-9B-Thinking", "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

Recibir y guardar resultados

Ailoot Ultra · OpenAI Chat

JSON or SSE

Conserva todos los resultados completados

Conserva todas las respuestas, archivos y partes de contenido completos recibidos.

Conserva todos los bloques de contenido, los ID de llamadas a herramientas, las firmas de razonamiento que se devuelvan, todos los incrementos SSE y los datos completos de consumo. El primer fragmento de texto no es el resultado completo.

Si es necesario revisar la respuesta original

Conserva el X-Client-Request-ID original, la respuesta y las cabeceras. Un resultado desconocido o result_pending_check no autoriza una segunda creación.

Campos de respuesta
CampoTipo
Campochoices[]Tipoobject
CampousageTipoobject
Errores y siguientes pasos
RespuestaCondiciónSiguiente paso
Respuesta400 · invalid_request_errorCondiciónUn campo obligatorio, el selector de modelo, el tipo o la representación de la entrada no son válidos.Siguiente pasoRevisa los detalles de validación devueltos antes de preparar una solicitud independiente.
RespuestaCondiciónLa solicitud original o su resultado son desconocidos o requieren una comprobación.Siguiente pasoConserva los identificadores y las cabeceras originales; consulta únicamente los registros de estado o de la biblioteca admitidos. No vuelvas a enviar la solicitud de creación.

Alias

Alias del modelo

Ailoot Ultra THUDM/GLM-4.1V-9B-Thinking

Alias de rutas de métodos

/chat/completions

ID de modelo relacionados

THUDM/GLM-4.1V-9B-Thinking

", "method_identity": { "effective_request_model_id": "THUDM/GLM-4.1V-9B-Thinking", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "THUDM/GLM-4.1V-9B-Thinking", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|THUDM%2FGLM-4.1V-9B-Thinking", "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 campo obligatorio, el selector de modelo, el tipo o la representación de la entrada no son válidos.", "http_status": 400, "recovery": "Revisa los detalles de validación devueltos antes de preparar una solicitud independiente.", "type": "invalid_request_error" }, { "condition": "La solicitud original o su resultado son desconocidos o requieren una comprobación.", "http_status": null, "recovery": "Conserva los identificadores y las cabeceras originales; consulta únicamente los registros de estado o de la biblioteca admitidos. No vuelvas a enviar la solicitud de creación.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Conserva el X-Client-Request-ID original, la respuesta y las cabeceras. Un resultado desconocido o result_pending_check no autoriza una segunda creación.", "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": "Conserva todos los bloques de contenido, los ID de llamadas a herramientas, las firmas de razonamiento que se devuelvan, todos los incrementos SSE y los datos completos de consumo. El primer fragmento de texto no es el resultado completo.", "every_actual_output": true, "family": "text", "fields": [ { "name": "choices[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" }, "parameters": [ { "conditions": "Usa exactamente este selector de enrutamiento de Ailoot.", "default_known": false, "enum": [ "THUDM/GLM-4.1V-9B-Thinking" ], "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": [ "THUDM/GLM-4.1V-9B-Thinking" ], "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": "THUDM/GLM-4.1V-9B-Thinking" }, "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": [ "Usa exactamente este selector de enrutamiento de Ailoot.", "Este protocolo transporta contenido de imagen cuando el modelo concreto seleccionado admite visión. Que el protocolo admita la solicitud no demuestra que todos los modelos puedan procesar imágenes." ], "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\": \"THUDM/GLM-4.1V-9B-Thinking\", \"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": "Tarifas cero solo para texto", "value": "La caché, las herramientas y el contenido multimedia siguen sus respectivas condiciones de precio, indicadas por separado.", "when": "Para entrada y salida de texto únicamente" } ], "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": "THUDM/GLM-4.1V-9B-Thinking", "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": "THUDM/GLM-4.1V-9B-Thinking", "nativeProvenance": { "input_facts_canonical_sha256": "4b925e81300d560c456724720b2fab7b41ea9e142c6d87458529496ae0db6f6d", "input_html_sha256": "8385f5911ebf3d413e858e500d0619f6d831ecde256d9f6f7891ea945c6ff4f1", "private_audit_sha256": "0d3199e5eea5da078b16cc9e4f2f456b1fdcb039fb095583377674fddfce279f", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/es/thudm-glm-4-1v-9b-thinking/", "description": "Chat GLM de texto e imágenes para preguntas visuales que requieren respuesta escrita.", "locale": "es", "md_url": "https://ailoot.ai/models/es/thudm-glm-4-1v-9b-thinking/index.md", "title": "THUDM/GLM-4.1V-9B-Thinking — Ailoot", "url": "https://ailoot.ai/models/es/thudm-glm-4-1v-9b-thinking/" }, "rawModel": { "about": "THUDM/GLM-4.1V-9B-Thinking puede recibir una conversación de texto mediante la API /v1/chat/completions de Ailoot. Para una tarea de texto, envía el ID literal del modelo y un array messages con un role y content de texto en cada entrada. La descripción puede incluir el enunciado de un problema, texto extraído de documentos, mediciones o la descripción de una escena que deba abordar la respuesta.\n\nExplicita la relación entre la información y la pregunta. Para una explicación técnica, proporciona las definiciones y los valores utilizados en el argumento. Para una comparación de documentos, etiqueta los fragmentos e indica los criterios de comparación. Solicita un resultado que separe las observaciones proporcionadas de la conclusión para poder comprobar cada paso con el material de la conversación.\n\nUna solicitud habitual devuelve JSON; stream activa SSE. Conserva la respuesta completa, incluido cualquier contenido adicional devuelto, y guarda usage. Revisa el resultado escrito con los hechos originales antes de utilizarlo en un informe o continuar la discusión.", "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": "Consulta los precios completos de la configuración en los detalles." } ], "ctx": null, "formats": [ "chat" ], "id": "THUDM/GLM-4.1V-9B-Thinking", "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 campo obligatorio, el selector de modelo, el tipo o la representación de la entrada no son válidos.", "http_status": 400, "recovery": "Revisa los detalles de validación devueltos antes de preparar una solicitud independiente.", "type": "invalid_request_error" }, { "condition": "La solicitud original o su resultado son desconocidos o requieren una comprobación.", "http_status": null, "recovery": "Conserva los identificadores y las cabeceras originales; consulta únicamente los registros de estado o de la biblioteca admitidos. No vuelvas a enviar la solicitud de creación.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_or_streamed", "status": [], "unknown": "Conserva el X-Client-Request-ID original, la respuesta y las cabeceras. Un resultado desconocido o result_pending_check no autoriza una segunda creación.", "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": "Conserva todos los bloques de contenido, los ID de llamadas a herramientas, las firmas de razonamiento que se devuelvan, todos los incrementos SSE y los datos completos de consumo. El primer fragmento de texto no es el resultado completo.", "every_actual_output": true, "family": "text", "fields": [ { "name": "choices[]", "type": "object" }, { "name": "usage", "type": "object" } ], "format": "JSON or SSE" }, "parameters": [ { "conditions": "Usa exactamente este selector de enrutamiento de Ailoot.", "default_known": false, "enum": [ "THUDM/GLM-4.1V-9B-Thinking" ], "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": [ "THUDM/GLM-4.1V-9B-Thinking" ], "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": "THUDM/GLM-4.1V-9B-Thinking" }, "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": [ "Usa exactamente este selector de enrutamiento de Ailoot.", "Este protocolo transporta contenido de imagen cuando el modelo concreto seleccionado admite visión. Que el protocolo admita la solicitud no demuestra que todos los modelos puedan procesar imágenes." ], "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\": \"THUDM/GLM-4.1V-9B-Thinking\", \"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": "Tarifas cero solo para texto", "value": "La caché, las herramientas y el contenido multimedia siguen sus respectivas condiciones de precio, indicadas por separado.", "when": "Para entrada y salida de texto únicamente" } ], "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": "THUDM/GLM-4.1V-9B-Thinking", "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": "THUDM/GLM-4.1V-9B-Thinking", "request_model_id": "THUDM/GLM-4.1V-9B-Thinking", "route_label": "Ultra" } ], "name": "THUDM/GLM-4.1V-9B-Thinking", "price": { "in": 0, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0, "sort_out": 0, "varies": false }, "short": "Usa THUDM/GLM-4.1V-9B-Thinking con una pregunta de texto y la información que debe analizar. La solicitud de chat de Ailoot devuelve una respuesta escrita como JSON o SSE.", "title": "THUDM/GLM-4.1V-9B-Thinking" }, "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": "Chat GLM de texto e imágenes para preguntas visuales que requieren respuesta escrita.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "9f9d7545c82ed6c2eae2e32842183448021c484f30d3c07d7a14d8f5547f8b93", "renderer_sha256": "b6d488b4bdee68568e5b17d2d4871b2ba1885e1032091b635a7a58ad2ca224e7" }, "sourceRevision": "a83ea3ab4eb0e3b5882e649e2f5a2f91483a600e7bff43286c19d7c0a0ab4bb0" }