---
title: "List Responses"
method: GET
path: "/v1/responses"
tags: ["responses-harmonized.openapi_other"]
---

# List Responses

`GET /v1/responses`

Get a list of all responses for the authenticated account.

Args:
    limit: Maximum number of responses to return (default: 20, max: 100)
    after: Cursor for pagination - return responses after this ID
    before: Cursor for pagination - return responses before this ID

## Query parameters

- `limit` integer
- `after` string, nullable
- `before` string, nullable

## Response `200`

Successful Response

- ResponseList — Response model for listing responses. Returned from the GET /v1/responses endpoint. Provides a paginated list of response objects with cursor-based pagination support.
  - `object` string — The object type, which is always 'list'.
  - `data` Response[], required — An array of response objects, sorted by creation time in descending order (most recent first).
    - `id` string, nullable — The unique identifier of the response. Will be None if store=False.
    - `object` string — The object type, which is always 'response'.
    - `created_at` integer, required — The Unix timestamp (in seconds) when the response was created.
    - `status` string, required — The status of the response. Can be 'completed', 'in_progress', 'incomplete', 'failed', or 'cancelled'.
    - `model` string, required — The model used to generate the response (e.g., `accounts/<ACCOUNT_ID>/models/<MODEL_ID>`).
    - `output` union[], required — An array of output items produced by the model. Can contain messages, tool calls, and tool outputs.
      - union
        - Message — Represents a message in a conversation.
          - `id` string, required — The unique identifier of the message.
          - `type` string — The object type, always 'message'.
          - `role` string, required — The role of the message sender. Can be 'user', 'assistant', or 'system'.
          - `content` MessageContent[], required — An array of content parts that make up the message. Each part has a type and associated data.
            - `type` string, required — The type of the content part. Can be 'input_text', 'output_text', 'image', etc.
            - `text` string, nullable — The text content, if applicable.
          - `status` string, required — The status of the message. Can be 'in_progress' or 'completed'.
        - ToolCall — Represents a tool call made by the model.
          - `id` string, required — The unique identifier of the tool call.
          - `type` string, required — The type of tool call. Can be 'function_call' or 'mcp_call'.
          - `call_id` string, nullable — The call ID for function calls, used to match with function_call_output.
          - `name` string, nullable — The name of the function to call (for function_call type).
          - `arguments` string, nullable — The arguments for the function call as a JSON string (for function_call type).
          - `status` string, nullable — The status of the tool call. Can be 'in_progress', 'completed', or 'incomplete'.
          - `function` object, nullable — The function definition for function tool calls. Contains 'name' and 'arguments' keys. Deprecated for function_call type.
          - `mcp` object, nullable — The MCP (Model Context Protocol) tool call definition for MCP tool calls.
        - ToolOutput — Represents the output/result of a tool call.
          - `type` string — The object type, always 'tool_output'.
          - `tool_call_id` string, required — The ID of the tool call that this output corresponds to.
          - `output` string, required — The output content from the tool execution.
    - `previous_response_id` string, nullable — The ID of the previous response in the conversation, if this response continues a conversation.
    - `usage` object, nullable — Token usage information for the request. Contains 'prompt_tokens', 'completion_tokens', and 'total_tokens'.
    - `error` object, nullable — Error information if the response failed. Contains 'type', 'code', and 'message' fields.
    - `incomplete_details` object, nullable — Details about why the response is incomplete, if status is 'incomplete'. Contains 'reason' field which can be 'max_output_tokens', 'max_tool_calls', or 'content_filter'.
    - `instructions` string, nullable — System instructions that guide the model's behavior. Similar to a system message.
    - `max_output_tokens` integer, nullable — The maximum number of tokens that can be generated in the response. Must be at least 1.
    - `max_tool_calls` integer, nullable — The maximum number of tool calls allowed in a single response. Must be at least 1.
    - `parallel_tool_calls` boolean — Whether to enable parallel function calling during tool use. Default is True.
    - `reasoning` object, nullable — Reasoning output from the model, if reasoning is enabled. Contains 'content' and 'type' fields.
    - `store` boolean, nullable — Whether to store this response for future retrieval. If False, the response will not be persisted and previous_response_id cannot reference it. Default is True.
    - `temperature` number — The sampling temperature to use, between 0 and 2. Higher values like 0.8 make output more random, while lower values like 0.2 make it more focused and deterministic. Default is 1.0.
    - `text` object, nullable — Text generation configuration parameters, if applicable.
    - `tool_choice` union — Controls which (if any) tool the model should use. Can be 'none', 'auto', 'required', or an object specifying a particular tool. Default is 'auto'.
      - string
      - object
    - `tools` object[] — A list of tools the model may call. Each tool is defined with a type and function specification following the OpenAI tool format. Supports 'function', 'mcp', 'sse', and 'python' tool types.
    - `top_p` number — An alternative to temperature sampling, called nucleus sampling, where the model considers the results of tokens with top_p probability mass. So 0.1 means only tokens comprising the top 10% probability mass are considered. Default is 1.0.
    - `truncation` string — The truncation strategy to use for the context. Can be 'auto' or 'disabled'. Default is 'disabled'.
    - `user` string, nullable — A unique identifier representing your end-user, which can help Fireworks to monitor and detect abuse.
    - `metadata` object, nullable — Set of up to 16 key-value pairs that can be attached to the response. Useful for storing additional information about the response in a structured format.
  - `has_more` boolean, required — Indicates whether there are more responses available beyond this page. If true, use the 'last_id' value as the 'after' cursor to fetch the next page.
  - `first_id` string, nullable — The ID of the first response in the current page. Used for pagination.
  - `last_id` string, nullable — The ID of the last response in the current page. Use this as the 'after' cursor to fetch the next page if has_more is true.

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api.md) · [All operations](https://skmtc.net/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/fireworks/fireworks-ai-anthropic-compatible-messages-api/versions/954d6bc5d922/schema)