Responses API

SeaCloud LLM Responses API uses the explicit OpenAI protocol prefix /openai/v1/responses.

Request

POST {BASE_URL}/openai/v1/responses

curl -sS "${BASE_URL}/openai/v1/responses" \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "input": "Write a three-step API integration checklist"
  }'

Streaming example

curl -sS "${BASE_URL}/openai/v1/responses?stream=true" \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "input": "Stream two suggestions",
    "stream": true
  }'

Response handling

• Non-streaming responses use the Responses API JSON shape.
• Streaming responses return SSE events.
• Use the usage field in the response as the source of truth for usage details.
• Use the Responses path listed in this documentation.