> ## Documentation Index
> Fetch the complete documentation index at: https://docs.relace.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# List Models

> Get the catalog for open-weight models hosted by Relace.

Each catalog entry includes context limits, current per-token pricing, and supported sampling parameters and features. Use the `id` field as the `model` parameter in [chat completions](/api-reference/open-models/chat-completions) requests.


## OpenAPI

````yaml GET /models
openapi: 3.0.1
info:
  title: Relace API
  description: API for accessing Relace code generation models.
  version: 1.0.0
  license:
    name: MIT
servers:
  - url: https://models.relace.ai
    description: Server for model API endpoints
  - url: https://api.relace.run
    description: Server for general infrastructure
security:
  - bearerAuth: []
paths:
  /models:
    get:
      description: Get the catalog for open-weight models hosted by Relace.
      responses:
        '200':
          description: The hosted model catalog
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelsResponse'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error401'
      servers:
        - url: https://models.relace.ai
components:
  schemas:
    ModelsResponse:
      type: object
      properties:
        data:
          type: array
          items:
            type: object
            properties:
              id:
                type: string
                description: Model ID to pass as `model` in chat completions requests
              name:
                type: string
                description: Human-readable model name
              description:
                type: string
                description: What the model is and how to use it
              context_length:
                type: integer
                description: Maximum context length in tokens
              max_output_length:
                type: integer
                description: Maximum output length in tokens
              quantization:
                type: string
                description: Quantization the model is served at, e.g. `fp4`, `fp8`, `bf16`
              input_modalities:
                type: array
                items:
                  type: string
                description: Accepted input modalities, e.g. `text`, `image`
              output_modalities:
                type: array
                items:
                  type: string
                description: Produced output modalities
              pricing:
                type: object
                properties:
                  prompt:
                    type: string
                    description: Price per prompt token, in dollars
                  completion:
                    type: string
                    description: Price per completion token, in dollars
                  input_cache_reads:
                    type: string
                    description: >-
                      Price per prompt token served from the prefix cache, in
                      dollars
                description: Per-token prices, as decimal strings in dollars
              supported_sampling_parameters:
                type: array
                items:
                  type: string
                description: Sampling parameters the model accepts
              supported_features:
                type: array
                items:
                  type: string
                description: >-
                  Supported features, e.g. `tools`, `json_mode`,
                  `structured_outputs`, `reasoning`
          description: The available hosted models
    Error401:
      type: object
      properties:
        error:
          type: string
          description: Error message
          example: Authorized header required
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Relace API key Authorization header using the Bearer scheme.

````