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

# List LLM Models

> Returns every LLM provider and model an agent can use, the platform default model, and which models need your own provider API key (the agent's LLM `apiKey`) and from when. Without your key, a model whose date has passed is refused when you save the agent.



## OpenAPI

````yaml /api-reference/openapi.json get /v1/voice-agents/llm-catalog
openapi: 3.0.1
info:
  title: Hamsa API
  description: >-
    The Hamsa API: voice agents and their calls, phone numbers, batch calls and
    knowledge bases; speech to text, text to speech, voices and AI content.
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://api.tryhamsa.com
security: []
paths:
  /v1/voice-agents/llm-catalog:
    get:
      summary: List LLM providers and models
      description: >-
        Returns every LLM provider and model an agent can use, the platform
        default model, and which models need your own provider API key (the
        agent's LLM `apiKey`) and from when. Without your key, a model whose
        date has passed is refused when you save the agent.
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    example: true
                  message:
                    type: string
                    example: success
                  data:
                    type: object
                    properties:
                      defaultModel:
                        type: object
                        description: The model agents use when you don't pick one.
                        properties:
                          provider:
                            type: string
                            example: Gemini
                          model:
                            type: string
                            example: gemini-3.5-flash-lite
                      providers:
                        type: array
                        items:
                          $ref: '#/components/schemas/LlmCatalogProvider'
                    example:
                      defaultModel:
                        provider: Gemini
                        model: gemini-3.5-flash-lite
                      providers:
                        - provider: OpenAI
                          enforcementLevel: partial
                          models:
                            - model: GPT-5
                              ownKey: true
                              status: optional_until_date
                              enforceFrom: '2026-12-01T00:00:00.000Z'
                            - model: GPT-5-Mini
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: GPT-5-Nano
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: GPT-5.4-mini
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: gpt-6-luna
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: GPT-4.1
                              ownKey: true
                              status: optional_until_date
                              enforceFrom: '2026-12-01T00:00:00.000Z'
                            - model: GPT-4.1-Mini
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: GPT-4.1-Nano
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: GPT-4o
                              ownKey: true
                              status: optional_until_date
                              enforceFrom: '2026-12-01T00:00:00.000Z'
                            - model: GPT-4o-mini
                              ownKey: false
                              status: free
                              enforceFrom: null
                        - provider: Gemini
                          enforcementLevel: partial
                          models:
                            - model: Gemini 2.5-Pro
                              ownKey: true
                              status: optional_until_date
                              enforceFrom: '2026-12-01T00:00:00.000Z'
                            - model: Gemini 2.5-Flash
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: gemini-3.1-flash-lite
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: gemini-3.5-flash-lite
                              ownKey: false
                              status: free
                              enforceFrom: null
                        - provider: Custom
                          enforcementLevel: full
                          models: []
                        - provider: Groq
                          enforcementLevel: none
                          models:
                            - model: openai/gpt-oss-120b
                              ownKey: false
                              status: free
                              enforceFrom: null
                            - model: openai/gpt-oss-20b
                              ownKey: false
                              status: free
                              enforceFrom: null
        '401':
          description: 'Unauthorized: missing or invalid API key.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorSchema'
        '500':
          description: Server Side Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorSchema'
      security:
        - ApiKeyAuth: []
components:
  schemas:
    LlmCatalogProvider:
      type: object
      properties:
        provider:
          type: string
          enum:
            - OpenAI
            - Gemini
            - Custom
            - Groq
          description: LLM provider.
          example: OpenAI
        enforcementLevel:
          type: string
          enum:
            - full
            - partial
            - none
          description: >-
            How many of the provider's models need your own key: `full` all of
            them (always for `Custom`), `partial` some, `none` none.
          example: partial
        models:
          type: array
          items:
            $ref: '#/components/schemas/LlmCatalogModel'
          description: >-
            The models you can pick. Empty for `Custom`, which takes any model
            name on your own endpoint.
    ErrorSchema:
      type: object
      properties:
        code:
          type: integer
          description: >-
            Service error code: the HTTP status with a service prefix (for
            example `8404`). Missing when the service has no code for that
            status.
          example: 8404
        message:
          type: string
          description: >-
            What went wrong. Some services (calls and recordings) put the error
            key here, for example `CallNotFoundOrUnavailable`, and send no
            `messageKey`.
          example: Policy not found!
        messageKey:
          type: string
          description: >-
            Stable key for the error, safe to match on in code. Not returned by
            every service.
          example: PolicyNotFound
        params:
          type: object
          additionalProperties: true
          description: >-
            Details for some errors (for example `reason`). Not returned by
            every service.
          example:
            reason: NO_DRAFT
    LlmCatalogModel:
      type: object
      properties:
        model:
          type: string
          description: Model name to send as the agent's LLM model.
          example: GPT-5
        ownKey:
          type: boolean
          description: >-
            `true` when the model needs your own provider API key (on its
            `enforceFrom` date or now).
          example: true
        status:
          type: string
          enum:
            - required
            - optional_until_date
            - free
          description: >-
            `required`: your own key is needed now. `optional_until_date`: works
            without your key until `enforceFrom` (or no date is set yet).
            `free`: never needs your key.
          example: optional_until_date
        enforceFrom:
          type: string
          format: date-time
          nullable: true
          description: >-
            From when the model needs your own key. `null` when it never does,
            or no date is set yet.
          example: '2026-12-01T00:00:00.000Z'
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: Authorization
      description: >-
        Pass the API key in the Authorization header, You need to put Token
        keyword before the API key. e.g. 'Authorization: Token <api-key>'

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.