Responses API

Compatible with OpenAI's next-generation Responses API. It's similar to chat completions, but responses are kept as a server-side object; you can create, fetch, cancel and list their inputs.

Create a response

POST/v1/responses

curl https://app.qevron.ai/v1/responses \
  -H "Authorization: Bearer $QEVRON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "verinova",
    "input": "Explain AI in three bullet points."
  }'

resp = client.responses.create(
    model="verinova",
    input="Explain AI in three bullet points.",
)
print(resp.id, resp.status)

Response

{
  "object": "response",
  "id": "resp_abc123",
  "status": "completed",
  "created_at": 1716200000,
  "usage": { "input_tokens": 12, "output_tokens": 64, "total_tokens": 76 }
}

status values: in_progress, completed, failed, cancelled.

Fetch a response

GET/v1/responses/{response_id}

curl https://app.qevron.ai/v1/responses/resp_abc123 \
  -H "Authorization: Bearer $QEVRON_API_KEY"

Delete a response

DELETE/v1/responses/{response_id}

A successful delete returns 204 No Content.

Cancel a response

POST/v1/responses/{response_id}/cancel

Cancels an in-progress (in_progress) response.

List input items

GET/v1/responses/{response_id}/input_items

Returns the list of input items given to the response.

TIP

For simple text generation, Chat Completions is usually more practical. Prefer the Responses API for stateful, advanced workflows.