Inference

Create a response (OpenAI Responses API)

OpenAI Responses API for GPT models on Azure Government OpenAI and AWS GovCloud Bedrock. This is the endpoint Codex CLI targets when configured with wire_api = "responses". A thin proxy to the provider's native Responses API, restricted to GPT models. The gateway is stateless: store: true and previous_response_id are rejected with 400.

post/v1/responses

Request

  • Base URL: https://api.consus.io
  • URL: https://api.consus.io/v1/responses
  • Auth: API key in header x-api-key

Request body

modelstring required

Composite GPT model ID, e.g. gpt-5.6-sol:itar.

instructionsstring
toolsobject[]
max_output_tokensinteger
temperaturenumber
top_pnumber
parallel_tool_callsboolean
metadataobject
streamboolean
storefalse

Must be false or omitted — the gateway is stateless and rejects true with 400.

previous_response_idstring

Not accepted — rejected with 400. Send the full input array each turn.

Response

Provider response payload (or, with stream: true, a text/event-stream).

idstring
objectstring
created_atinteger
statusstring
modelstring
outputobject[]
x_consus_governanceobject

Example response

{
  "object": "response"
}

Changes

No recorded changes to this operation across all 1 revision of this API.