openapi: 3.2.0
info:
  title: LiteLLM Responses API
  description: 'Proxy Server to call 100+ LLMs in the OpenAI format. **Customize Swagger Docs**


    👉 ```LiteLLM Admin Panel on /ui```. Create, Edit Keys with SSO. Having issues? Try ```Fallback Login```


    💸 ```LiteLLM Model Cost Map```.


    🔎 ```LiteLLM Model Hub```. See available models on the proxy. **Docs**'
  version: 1.102.1
tags:
- name: Responses
paths:
  /openai/v1/responses:
    post:
      tags:
      - Responses
      summary: Responses Api
      description: 'Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses


        Supports background mode with polling_via_cache for partial response retrieval.

        When background=true and polling_via_cache is enabled, returns a polling_id immediately

        and streams the response in the background, updating Redis cache.


        ```bash

        # Normal request

        curl -X POST http://localhost:4000/v1/responses -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Tell me about AI"

        }''


        # Background request with polling

        curl -X POST http://localhost:4000/v1/responses -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Tell me about AI",

        "background": true

        }''

        ```'
      operationId: responses_api_openai_v1_responses_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /responses:
    post:
      tags:
      - Responses
      summary: Responses Api
      description: 'Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses


        Supports background mode with polling_via_cache for partial response retrieval.

        When background=true and polling_via_cache is enabled, returns a polling_id immediately

        and streams the response in the background, updating Redis cache.


        ```bash

        # Normal request

        curl -X POST http://localhost:4000/v1/responses -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Tell me about AI"

        }''


        # Background request with polling

        curl -X POST http://localhost:4000/v1/responses -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Tell me about AI",

        "background": true

        }''

        ```'
      operationId: responses_api_responses_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /v1/responses:
    post:
      tags:
      - Responses
      summary: Responses Api
      description: 'Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses


        Supports background mode with polling_via_cache for partial response retrieval.

        When background=true and polling_via_cache is enabled, returns a polling_id immediately

        and streams the response in the background, updating Redis cache.


        ```bash

        # Normal request

        curl -X POST http://localhost:4000/v1/responses -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Tell me about AI"

        }''


        # Background request with polling

        curl -X POST http://localhost:4000/v1/responses -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Tell me about AI",

        "background": true

        }''

        ```'
      operationId: responses_api_v1_responses_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /cursor/v1/models:
    get:
      tags:
      - Responses
      summary: Cursor Model List
      description: 'OpenAI-compatible model listing for the Cursor BYOK base URL.


        Clients pointed at `/cursor` as an OpenAI-compatible base URL resolve and

        verify models via `GET {base}/models` (the OpenAI SDK contract). Without this

        route those requests fall through to the Cursor Cloud Agents passthrough, which

        demands a Cursor API key and 401s, so key verification silently fails before any

        chat request is ever sent. Delegates to the standard `/v1/models` handler.'
      operationId: cursor_model_list_cursor_v1_models_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /cursor/models:
    get:
      tags:
      - Responses
      summary: Cursor Model List
      description: 'OpenAI-compatible model listing for the Cursor BYOK base URL.


        Clients pointed at `/cursor` as an OpenAI-compatible base URL resolve and

        verify models via `GET {base}/models` (the OpenAI SDK contract). Without this

        route those requests fall through to the Cursor Cloud Agents passthrough, which

        demands a Cursor API key and 401s, so key verification silently fails before any

        chat request is ever sent. Delegates to the standard `/v1/models` handler.'
      operationId: cursor_model_list_cursor_models_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /cursor/chat/completions:
    post:
      tags:
      - Responses
      summary: Cursor Chat Completions
      description: 'Cursor BYOK endpoint. Accepts both request shapes Cursor sends to its OpenAI-compatible

        base URL and always answers in chat completions format.


        Cursor agent mode sends Responses API format bodies (`input`, flat tool defs, `reasoning`,

        custom tools) to the chat/completions path while expecting chat completions responses;

        those are routed through the Responses API pipeline and converted back. Genuine chat

        completions bodies (`messages` present) are routed through the standard chat completions

        pipeline, after normalizing each level of the `tools` array and `tool_choice` to the chat

        completions shapes OpenAI requires. Cursor mixes Responses API shapes into chat bodies

        per level, independently: a flat tool def (`{"type": "custom", "name": "ApplyPatch", ...}`)

        gets nested under `custom`, and a flat grammar format

        (`{"type": "grammar", "definition", "syntax"}`) gets wrapped as

        `{"type": "grammar", "grammar": {...}}` wherever it appears, including inside tool defs

        Cursor already sent pre-nested.


        ```bash

        curl -X POST http://localhost:4000/cursor/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": [{"role": "user", "content": "Hello"}]

        }''

        Responds back in chat completions format.

        ```'
      operationId: cursor_chat_completions_cursor_chat_completions_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /openai/v1/responses/{response_id}:
    get:
      tags:
      - Responses
      summary: Get Response
      description: 'Get a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Returns cumulative cached content from background responses

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/get


        ```bash

        # Get polling response

        curl -X GET http://localhost:4000/v1/responses/litellm_poll_abc123 -H "Authorization: Bearer sk-1234"


        # Get provider response

        curl -X GET http://localhost:4000/v1/responses/resp_abc123 -H "Authorization: Bearer sk-1234"

        ```'
      operationId: get_response_openai_v1_responses__response_id__get
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Responses
      summary: Delete Response
      description: 'Delete a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Deletes from Redis cache

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/delete


        ```bash

        curl -X DELETE http://localhost:4000/v1/responses/resp_abc123 -H "Authorization: Bearer sk-1234"

        ```'
      operationId: delete_response_openai_v1_responses__response_id__delete
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /responses/{response_id}:
    get:
      tags:
      - Responses
      summary: Get Response
      description: 'Get a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Returns cumulative cached content from background responses

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/get


        ```bash

        # Get polling response

        curl -X GET http://localhost:4000/v1/responses/litellm_poll_abc123 -H "Authorization: Bearer sk-1234"


        # Get provider response

        curl -X GET http://localhost:4000/v1/responses/resp_abc123 -H "Authorization: Bearer sk-1234"

        ```'
      operationId: get_response_responses__response_id__get
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Responses
      summary: Delete Response
      description: 'Delete a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Deletes from Redis cache

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/delete


        ```bash

        curl -X DELETE http://localhost:4000/v1/responses/resp_abc123 -H "Authorization: Bearer sk-1234"

        ```'
      operationId: delete_response_responses__response_id__delete
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/responses/{response_id}:
    get:
      tags:
      - Responses
      summary: Get Response
      description: 'Get a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Returns cumulative cached content from background responses

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/get


        ```bash

        # Get polling response

        curl -X GET http://localhost:4000/v1/responses/litellm_poll_abc123 -H "Authorization: Bearer sk-1234"


        # Get provider response

        curl -X GET http://localhost:4000/v1/responses/resp_abc123 -H "Authorization: Bearer sk-1234"

        ```'
      operationId: get_response_v1_responses__response_id__get
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Responses
      summary: Delete Response
      description: 'Delete a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Deletes from Redis cache

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/delete


        ```bash

        curl -X DELETE http://localhost:4000/v1/responses/resp_abc123 -H "Authorization: Bearer sk-1234"

        ```'
      operationId: delete_response_v1_responses__response_id__delete
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /openai/v1/responses/{response_id}/input_items:
    get:
      tags:
      - Responses
      summary: Get Response Input Items
      description: List input items for a response.
      operationId: get_response_input_items_openai_v1_responses__response_id__input_items_get
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /responses/{response_id}/input_items:
    get:
      tags:
      - Responses
      summary: Get Response Input Items
      description: List input items for a response.
      operationId: get_response_input_items_responses__response_id__input_items_get
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/responses/{response_id}/input_items:
    get:
      tags:
      - Responses
      summary: Get Response Input Items
      description: List input items for a response.
      operationId: get_response_input_items_v1_responses__response_id__input_items_get
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /openai/v1/responses/compact:
    post:
      tags:
      - Responses
      summary: Compact Response
      description: 'Compact a response by running a compaction pass over a conversation.


        Returns encrypted, opaque items that can be used to reduce context size.


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/compact


        ```bash

        curl -X POST http://localhost:4000/v1/responses/compact -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": [{"role": "user", "content": "Hello"}]

        }''

        ```'
      operationId: compact_response_openai_v1_responses_compact_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /responses/compact:
    post:
      tags:
      - Responses
      summary: Compact Response
      description: 'Compact a response by running a compaction pass over a conversation.


        Returns encrypted, opaque items that can be used to reduce context size.


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/compact


        ```bash

        curl -X POST http://localhost:4000/v1/responses/compact -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": [{"role": "user", "content": "Hello"}]

        }''

        ```'
      operationId: compact_response_responses_compact_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /v1/responses/compact:
    post:
      tags:
      - Responses
      summary: Compact Response
      description: 'Compact a response by running a compaction pass over a conversation.


        Returns encrypted, opaque items that can be used to reduce context size.


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/compact


        ```bash

        curl -X POST http://localhost:4000/v1/responses/compact -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": [{"role": "user", "content": "Hello"}]

        }''

        ```'
      operationId: compact_response_v1_responses_compact_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /openai/v1/responses/input_tokens:
    post:
      tags:
      - Responses
      summary: Responses Input Tokens
      description: 'Count the input tokens of a Responses API request without calling the model.


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/input-tokens


        ```bash

        curl -X POST http://localhost:4000/v1/responses/input_tokens -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Hello, how are you?"

        }''

        ```


        Returns: `{"object": "response.input_tokens", "input_tokens": }`'
      operationId: responses_input_tokens_openai_v1_responses_input_tokens_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /responses/input_tokens:
    post:
      tags:
      - Responses
      summary: Responses Input Tokens
      description: 'Count the input tokens of a Responses API request without calling the model.


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/input-tokens


        ```bash

        curl -X POST http://localhost:4000/v1/responses/input_tokens -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Hello, how are you?"

        }''

        ```


        Returns: `{"object": "response.input_tokens", "input_tokens": }`'
      operationId: responses_input_tokens_responses_input_tokens_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /v1/responses/input_tokens:
    post:
      tags:
      - Responses
      summary: Responses Input Tokens
      description: 'Count the input tokens of a Responses API request without calling the model.


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/input-tokens


        ```bash

        curl -X POST http://localhost:4000/v1/responses/input_tokens -H "Content-Type: application/json" -H "Authorization: Bearer sk-1234" -d ''{

        "model": "gpt-4o",

        "input": "Hello, how are you?"

        }''

        ```


        Returns: `{"object": "response.input_tokens", "input_tokens": }`'
      operationId: responses_input_tokens_v1_responses_input_tokens_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /openai/v1/responses/{response_id}/cancel:
    post:
      tags:
      - Responses
      summary: Cancel Response
      description: 'Cancel a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Cancels background response and updates status in Redis

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/cancel


        ```bash

        # Cancel polling response

        curl -X POST http://localhost:4000/v1/responses/litellm_poll_abc123/cancel -H "Authorization: Bearer sk-1234"


        # Cancel provider response

        curl -X POST http://localhost:4000/v1/responses/resp_abc123/cancel -H "Authorization: Bearer sk-1234"

        ```'
      operationId: cancel_response_openai_v1_responses__response_id__cancel_post
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /responses/{response_id}/cancel:
    post:
      tags:
      - Responses
      summary: Cancel Response
      description: 'Cancel a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Cancels background response and updates status in Redis

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/cancel


        ```bash

        # Cancel polling response

        curl -X POST http://localhost:4000/v1/responses/litellm_poll_abc123/cancel -H "Authorization: Bearer sk-1234"


        # Cancel provider response

        curl -X POST http://localhost:4000/v1/responses/resp_abc123/cancel -H "Authorization: Bearer sk-1234"

        ```'
      operationId: cancel_response_responses__response_id__cancel_post
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/responses/{response_id}/cancel:
    post:
      tags:
      - Responses
      summary: Cancel Response
      description: 'Cancel a response by ID.


        Supports both:

        - Polling IDs (litellm_poll_*): Cancels background response and updates status in Redis

        - Provider response IDs: Passes through to provider API


        Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses/cancel


        ```bash

        # Cancel polling response

        curl -X POST http://localhost:4000/v1/responses/litellm_poll_abc123/cancel -H "Authorization: Bearer sk-1234"


        # Cancel provider response

        curl -X POST http://localhost:4000/v1/responses/resp_abc123/cancel -H "Authorization: Bearer sk-1234"

        ```'
      operationId: cancel_response_v1_responses__response_id__cancel_post
      security:
      - APIKeyHeader: []
      parameters:
      - name: response_id
        in: path
        required: true
        schema:
          type: string
          title: Response Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      description: Bearer token
      in: header
      name: x-litellm-api-key