Skip to main content
The Responses API is OpenAI’s stateful response protocol. AI Sonar exposes it only when the model details advertise the Responses request format and a same-protocol route is currently available; this is not inferred from a gpt-* name or provider. Native Responses requests stay on Responses endpoints and never fall back through Chat Completions. AI Sonar preserves the request JSON shape, including unknown fields, explicit null, and empty arrays, and forwards it best-effort. Unknown or future fields remain subject to the selected service’s support.

Request Body

string
required
ID of the model to use. See Models for available options.
string | array
Input for the response. It is optional when the request instead uses a reusable prompt or continues a stored response with previous_response_id.Each item can be:
  • message: A conversation message with role and content
  • function_call: A function call request
  • function_call_output: Output from a function call
For multimodal input, message.content can be either a plain string or an array of content blocks. For image-capable models such as GPT-5.4 variants, pass images as input_image blocks instead of embedding URLs or Base64 strings directly into plain text.Example content blocks:
  • { "type": "input_text", "text": "Describe this image" }
  • { "type": "input_image", "image_url": "https://example.com/image.jpg" }
  • { "type": "input_image", "image_url": "data:image/png;base64,..." }
string
System instructions for the model (equivalent to system message).
integer
Maximum number of tokens to generate.
number
default:"1"
Sampling temperature between 0 and 2.
array
A list of tools the model may call. AI Sonar forwards native tool definitions without maintaining a local hosted-tool whitelist; the selected service decides which types and combinations are supported.
boolean
default:"false"
If true, returns a stream of events.
string
ID of a previous response to continue the conversation from.
boolean
default:"true"
Whether to store the response for later retrieval.
boolean
default:"false"
Whether to ask the selected native Responses service to run asynchronously. AI Sonar does not infer support from the provider or model name: a clear service rejection is returned unchanged, while an accepted queued or in-progress response remains trackable until it reaches a terminal state, even if the client never retrieves it.
object
Reference to a reusable prompt template and variables.
object
Metadata to attach to the response for tracking purposes.
object
Text generation configuration options. Behavior for text.format depends on the selected model and routed path; it is not guaranteed uniformly across every model.
boolean
default:"true"
Whether to allow multiple tool calls in parallel.
number
Nucleus sampling parameter (0-1).
object
Reasoning configuration for reasoning-enabled models such as GPT-5 family variants.
  • effort (string): Reasoning effort level (low, medium, high)

Response

string
Unique identifier for the response.
string
Always response.
integer
Unix timestamp of when the response was created.
array
List of output items generated by the model.
object
Token usage statistics.
Valid response states include queued, in_progress, completed, incomplete, failed, and cancelled. An HTTP 200 response whose native status is failed or incomplete is returned as-is; it is not rewritten to a gateway 502.

Lifecycle boundaries

  • GET /v1/responses/{id} retrieves the stored response and supports include, include_obfuscation, stream, and starting_after.
  • DELETE /v1/responses/{id} deletes a stored response. It is not a cancellation endpoint.
  • POST /v1/responses/compact returns the native response.compaction contract.
  • Public cancel, input-items, and input-tokens endpoints are not currently exposed.