Responses

POST /v1/responses — OpenAI Responses format, with streamed reasoning summaries.

POST https://inference-api.openserv.ai/v1/responses

OpenAI Responses format. Use it to receive the reasoning trace alongside the answer. OpenAI models only — other models are not supported on this endpoint. Use chat completions for everything else.

Request

Authorization · string · required

Bearer $SERV_API_KEY.

model · string · required

An OpenAI model ID from the catalog, for example gpt-5.4.

input · string | array · required

The prompt — a string, or an array of input items.

instructions · string · required

The system prompt. SERV requires one.

reasoning · object

Reasoning controls, for example { "effort": "medium", "summary": "auto" }.

max_output_tokens · integer

Maximum number of tokens to generate.

tools · array

Function definitions, in OpenAI format.

stream · boolean · default: "false"

Stream the response as server-sent events.

All other OpenAI Responses parameters are accepted and forwarded to the model.

Response

id · string

Unique identifier for the response.

object · string

Always "response".

model · string

The model used.

output_text · string

Convenience field with the generated text.

output · array

The full output items, including reasoning items when reasoning is enabled.

usage · object

Token counts: input_tokens, output_tokens, total_tokens.

curl

curl https://inference-api.openserv.ai/v1/responses \
  -H "Authorization: Bearer $SERV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "instructions": "You are a careful reasoner.",
    "input": "Hello!"
  }'

{
  "id": "resp_...",
  "object": "response",
  "model": "gpt-5.4",
  "output_text": "Hello! How can I help?",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [{ "type": "output_text", "text": "Hello! How can I help?" }]
    }
  ],
  "usage": { "input_tokens": 16, "output_tokens": 7, "total_tokens": 23 }
}