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

# List LLM Models

> List the LLMs your team can run an agent on, each with its token rates. The rates are set by the LLM providers and change when a provider changes its pricing.



## OpenAPI

````yaml get /v1/agent/llm-models
openapi: 3.1.0
info:
  title: FishAudio OpenAPI
  version: '1'
servers:
  - description: Fish Audio API
    url: https://api.fish.audio
security: []
tags: []
paths:
  /v1/agent/llm-models:
    get:
      tags:
        - Agent LLM Models
      summary: List LLM Models
      description: >-
        List the LLMs your team can set as `llm.model` on an agent's config,
        each

        with its token rates. The rates are set by the LLM providers and change

        when a provider changes its pricing. The response carries the rates in

        force now.
      responses:
        '200':
          description: Request fulfilled, document follows
          headers: {}
          content:
            application/json:
              schema:
                properties:
                  llm_models:
                    items:
                      $ref: '#/components/schemas/PublicLLMModel'
                    title: Llm Models
                    type: array
                required:
                  - llm_models
                type: object
        '401':
          description: No permission -- see authorization schemes
          headers: {}
          content:
            application/json:
              schema:
                properties:
                  status:
                    title: Status
                    type: integer
                  message:
                    title: Message
                    type: string
                  reason:
                    anyOf:
                      - type: string
                      - type: 'null'
                    default: null
                    title: Reason
                required:
                  - status
                  - message
                type: object
        '503':
          description: The server cannot process the request due to a high load
          headers: {}
          content:
            application/json:
              schema:
                properties:
                  status:
                    title: Status
                    type: integer
                  message:
                    title: Message
                    type: string
                  reason:
                    anyOf:
                      - type: string
                      - type: 'null'
                    default: null
                    title: Reason
                required:
                  - status
                  - message
                type: object
      security:
        - BearerAuth: []
components:
  schemas:
    PublicLLMModel:
      properties:
        id:
          description: The model id, as set in `llm.model` on an agent's config.
          enum:
            - google/gemini-3.5-flash-lite
            - google/gemini-3.6-flash
            - google/gemini-3.8-flash
            - google/gemini-3.6-flash-priority
            - google/gemini-3.8-flash-priority
            - google/gemini-3.5-flash-lite-priority
            - google/gemini-2.5-flash
            - google/gemma-4-26b-a4b-it
            - anthropic/claude-haiku-4.5
            - anthropic/claude-sonnet-4.6
            - anthropic/claude-sonnet-5.5
            - anthropic/claude-opus-5.5
            - anthropic/claude-fable-5.1
            - anthropic/claude-fable-5.2
            - openai/gpt-5.6-luna
            - openai/gpt-6-luna
            - openai/gpt-5
            - openai/gpt-6.1-sol
            - openai/gpt-6.1-terra
            - openai/gpt-6-astra
            - openai/gpt-4o
            - openai/gpt-4.1
            - openai/gpt-5.6-luna-fast
            - openai/gpt-6-luna-fast
            - openai/gpt-6.1-terra-fast
            - openai/gpt-6.1-sol-fast
            - openai/gpt-6-astra-fast
            - openai/gpt-4o-fast
            - openai/gpt-4.1-fast
          title: Id
          type: string
        included_in_conversation_rate:
          description: >-
            Whether the conversation rate covers this model's tokens. When true,
            a conversation on the model has no LLM charge, and its rates apply
            where no conversation rate is charged, such as Simulation tests.
          title: Included In Conversation Rate
          type: boolean
        usd_per_million_tokens:
          $ref: '#/components/schemas/PublicLLMTokenRates'
          description: >-
            What the model's tokens cost in USD per one million tokens, by token
            category, as decimal strings.
        long_context:
          anyOf:
            - $ref: '#/components/schemas/PublicLLMLongContextRates'
            - type: 'null'
          description: >-
            Rates that replace `usd_per_million_tokens` on a request with a long
            prompt. Null when the model has no such tier.
      required:
        - id
        - included_in_conversation_rate
        - usd_per_million_tokens
        - long_context
      title: PublicLLMModel
      type: object
    PublicLLMTokenRates:
      properties:
        input:
          description: Input tokens neither read from nor written to the prompt cache.
          title: Input
          type: string
        cache_read:
          description: Input tokens read from the prompt cache.
          title: Cache Read
          type: string
        cache_write_5m:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            Input tokens written to the prompt cache. Null when the model has no
            cache write charge.
          title: Cache Write 5M
        output:
          description: Output tokens, reasoning tokens included.
          title: Output
          type: string
      required:
        - input
        - cache_read
        - cache_write_5m
        - output
      title: PublicLLMTokenRates
      type: object
    PublicLLMLongContextRates:
      properties:
        over_prompt_tokens:
          description: >-
            A request whose prompt is larger than this many tokens bills at
            these rates. The prompt is its input, cache read and cache write
            tokens together.
          title: Over Prompt Tokens
          type: integer
        usd_per_million_tokens:
          $ref: '#/components/schemas/PublicLLMTokenRates'
      required:
        - over_prompt_tokens
        - usd_per_million_tokens
      title: PublicLLMLongContextRates
      type: object
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer

````

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