Create a stateless response

OpenAI Responses-compatible text, vision, structured-output, and function-calling API. Set stream=true for typed lifecycle events.

post/responses

Request

  • Base URL: https://www.ninjachat.ai/api/v1
  • URL: https://www.ninjachat.ai/api/v1/responses
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Safely retry the same logical write without duplicate billing or execution.

Request body

modelstring
modelsstring[]
instructionsstring
max_output_tokensinteger

Maximum completion tokens, including reasoning where the provider counts it. Must fit the selected provider's output and context limits. Defaults to 2048 when omitted.

temperaturenumber
top_pnumber
streamboolean
storefalse
parallel_tool_callsboolean
metadataobject
userstring

Response

Completed response or SSE stream.

idstring required
object'response' required
created_atinteger required
status'completed' | 'incomplete' required
errorunknown required
instructionsstring nullable required
max_output_tokensinteger nullable required
modelstring required
output_textstring required
parallel_tool_callsboolean required
previous_response_idunknown required
storefalse required
cost_usdnumber required
providerstring nullable required
request_idstring required
metadataobject required

Changes

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