Sign in
responses.openapi_other

Create Response

Creates a model response, optionally interacting with custom tools via the Model Context Protocol (MCP). This endpoint supports conversational continuation and streaming.

Explore our cookbooks for detailed examples:

post/v1/responses

Request body

modelstring required

The model to use for generating the response. Example: accounts/<ACCOUNT_ID>/models/<MODEL_ID>.

previous_response_idstring nullable

The ID of a previous response to continue the conversation from. When provided, the conversation history from that response will be automatically loaded.

instructionsstring nullable

System instructions that guide the model's behavior throughout the conversation. Similar to a system message.

max_output_tokensinteger nullable

The maximum number of tokens that can be generated in the response. Must be at least 1. If not specified, the model will generate up to its maximum context length.

max_tool_callsinteger nullable

The maximum number of tool calls allowed in a single response. Useful for controlling costs and limiting tool execution. Must be at least 1.

metadataobject nullable

Set of up to 16 key-value pairs that can be attached to the response. Useful for storing additional information in a structured format.

parallel_tool_callsboolean nullable

Whether to enable parallel function calling during tool use. When true, the model can call multiple tools simultaneously. Default is True.

reasoningobject nullable

Configuration for reasoning output. When enabled, the model will return its reasoning process along with the response.

storeboolean nullable

Whether to store the response. When set to false, the response will not be stored and will not be retrievable via the API. This is useful for ephemeral or sensitive data. See an example in our Controlling Response Storage cookbook. Default is True.

streamboolean nullable

Whether to stream the response back as Server-Sent Events (SSE). When true, tokens are sent incrementally as they are generated. Default is False.

temperaturenumber nullable

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.

textobject nullable

Text generation configuration parameters. Used for advanced text generation settings.

toolsobject[] nullable

A list of MCP tools the model may call. See our cookbooks for examples on basic MCP usage and streaming with MCP.

top_pnumber nullable

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. We generally recommend altering this or temperature but not both.

truncationstring nullable

The truncation strategy to use for the context when it exceeds the model's maximum length. Can be 'auto' (automatically truncate) or 'disabled' (return error if context too long). Default is 'disabled'.

userstring nullable

A unique identifier representing your end-user, which can help Fireworks to monitor and detect abuse. This can be a username, email, or any other unique identifier.

Response

Successful Response

idstring nullable

The unique identifier of the response. Will be None if store=False.

objectstring

The object type, which is always 'response'.

created_atinteger required

The Unix timestamp (in seconds) when the response was created.

statusstring required

The status of the response. Can be 'completed', 'in_progress', 'incomplete', 'failed', or 'cancelled'.

modelstring required

The model used to generate the response (e.g., accounts/<ACCOUNT_ID>/models/<MODEL_ID>).

previous_response_idstring nullable

The ID of the previous response in the conversation, if this response continues a conversation.

usageobject nullable

Token usage information for the request. Contains 'prompt_tokens', 'completion_tokens', and 'total_tokens'.

errorobject nullable

Error information if the response failed. Contains 'type', 'code', and 'message' fields.

incomplete_detailsobject 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'.

instructionsstring nullable

System instructions that guide the model's behavior. Similar to a system message.

max_output_tokensinteger nullable

The maximum number of tokens that can be generated in the response. Must be at least 1.

max_tool_callsinteger nullable

The maximum number of tool calls allowed in a single response. Must be at least 1.

parallel_tool_callsboolean

Whether to enable parallel function calling during tool use. Default is True.

reasoningobject nullable

Reasoning output from the model, if reasoning is enabled. Contains 'content' and 'type' fields.

storeboolean 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.

temperaturenumber

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.

textobject nullable

Text generation configuration parameters, if applicable.

toolsobject[]

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_pnumber

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.

truncationstring

The truncation strategy to use for the context. Can be 'auto' or 'disabled'. Default is 'disabled'.

userstring nullable

A unique identifier representing your end-user, which can help Fireworks to monitor and detect abuse.

metadataobject 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.

Changes

Changed in 3 of the 27 revisions of this API.7

  • 29a1e4db152c2See the full diff
    • ○

      added the optional property detail/items/ctx to the response with the 422 status

      response-optional-property-added

    • ○

      added the optional property detail/items/input to the response with the 422 status

      response-optional-property-added

  • 80bec85988ad4See the full diff
    • ○

      added the optional property output/items/anyOf[subschema #2: ToolCall]/arguments to the response with the 200 status

      response-optional-property-added

    • ○

      added the optional property output/items/anyOf[subschema #2: ToolCall]/call_id to the response with the 200 status

      response-optional-property-added

    • ○

      added the optional property output/items/anyOf[subschema #2: ToolCall]/name to the response with the 200 status

      response-optional-property-added

    • ○

      added the optional property output/items/anyOf[subschema #2: ToolCall]/status to the response with the 200 status

      response-optional-property-added

  • 311efdb2fa571See the full diff
    • ○

      endpoint added

      endpoint-added

    This revision also has 2 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog