API ReferencePlatformListings

List Available LLM Models

Retrieve a list of all available Large Language Models (LLMs) that can be used in Tasks. **Note**: This endpoint returns a plain array of models, not a paginated response. All available models are returned in a single request. By default, only active models are returned. Use the `include_retired=true` query parameter to include retired models. Optionally filter by vision (input) using one or more `vision` query parameters (e.g. `?vision=image&vision=pdf`). The model must support all listed: `image` (image input), `pdf` (PDF vision input). Use `output=image` to restrict to models that can generate images (supports_image_output). Each model entry includes standard fields like: - Unique identifier (`id`) - Provider information (`provider`) - Vendor information (`vendor`) - Model reference name (`name`) - Human-readable alias (`alias`) - Detailed description (`description`) - Vision support status (`supports_vision`) - Whether the model can process images - Image output support (`supports_image_output`) - Whether the model can generate images - Price tier (`price`) - Coarse comparison tier: cheap, average, or expensive - Speed tier (`speed`) - Coarse comparison tier: standard, fast, or ultra fast - Knowledge cutoff (`knowledge_cutoff`) - Date of most recent training data, when known - Maximum context window (`max_context_window`) - Disabled parameters (`disabled_params`) - When the model was retired (`retired`) - The model that replaces it (`replaced_by`) Models may have different capabilities, performance characteristics, and cost structures. Choose models based on your specific needs.

Authentication

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

OR
AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

Path parameters

org_idstringRequiredformat: "uuid"
The unique identifier of the organization.
project_idstringRequiredformat: "uuid"
The unique identifier of the project.

Query parameters

include_retiredbooleanOptionalDefaults to false
Include models that have been retired.
visionlist of enumsOptional

Filter by vision (input) capability. Repeat for multiple: image (supports_vision), pdf (supports_pdf_vision). Model must support all listed.

Allowed values:
outputenumOptional

Filter by output capability, e.g. image for models that can generate images (supports_image_output).

Allowed values:

Response

Successfully retrieved list of available LLM models
providerstring

The company that produces the LLM (e.g., OpenAI, Anthropic, Meta).

vendorstring

The service provider or platform hosting the model (e.g., OpenAI, Azure, Groq).

namestring
The model's reference name used for API calls.
aliasstring

Human-readable name for the model.

descriptionstring
Detailed description of the model's capabilities, context window, and knowledge cutoff.
supports_visionboolean
Whether the model can process and analyze images.
max_context_windowinteger>=0
Maximum number of tokens the model can process in a single request.
idstringformat: "uuid"
supports_image_outputbooleanDefaults to false
Whether the model can generate images as output.
supports_pdf_visionbooleanDefaults to false
Whether the model can process PDFs as visual input.
supports_tool_callingbooleanDefaults to false
Whether the model supports tool calling APIs.
supports_context_cachingbooleanDefaults to false

Whether the model supports provider-native context caching.

priceenum or null
Coarse model price tier for selector comparison.
speedenum or null
Coarse model inference speed tier for selector comparison.
knowledge_cutoffdate or null
Date of the model's most recent training data, when known.
pdf_vision_configobject or null
Configuration limits for PDF vision processing.
model_paramsmap from strings to any or null
JSON Schema defining allowed model parameters for this model. Each parameter name maps to a JSON Schema specification defining its type, constraints, and validation rules.
createdstring or null
modifiedstring or null
replaced_bystring or nullformat: "uuid"
retiredstring or null
llm_model_commentslist of objectsDefaults to []

Errors

400
Bad Request Error
401
Unauthorized Error
403
Forbidden Error
404
Not Found Error
422
Unprocessable Entity Error
500
Internal Server Error