Skip to main content
POST
OpenAI Responses

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
string
required

ID of the GPT-series chat model to use. See Models for the current model list, pricing, and endpoint support.

Example:

"gpt-5.3-codex"

input
required

Text input or Responses API input items.

Example:

"Reply with exactly one word: pong"

instructions
string

Optional system or developer instructions.

max_output_tokens
integer

Maximum number of output tokens to generate.

Example:

1024

stream
boolean
default:false

If true, stream typed Responses API events over SSE.

reasoning
object

Optional reasoning controls, such as { "effort": "none" }. Support can vary by selected model and provider.

text
object

Optional text output controls.

temperature
number

Sampling temperature.

Required range: 0 <= x <= 2
Example:

1

top_p
number

Nucleus sampling parameter.

Required range: 0 <= x <= 1
Example:

1

previous_response_id
string

Optional previous response ID for multi-turn clients that use response chaining. Support can vary by selected model and provider.

store
boolean

Whether the response should be stored when supported by the provider. Support can vary by selected model and provider.

metadata
object

Optional metadata attached to the response. Support can vary by selected model and provider.

tools
object[]

Optional Responses API tools. Support can vary by selected model and provider.

tool_choice

Tool selection strategy. Support can vary by selected model and provider.

Available options:
auto,
none

Response

Responses API result.

id
string
Example:

"resp_abc123"

object
string
Example:

"response"

status
string
Example:

"completed"

model
string
Example:

"gpt-5.3-codex"

output
object[]
output_text
string

Flattened text output when available.

Example:

"pong"

usage
object