Skip to main content
DocumentationDevelopers

Responses

OpenAI's Responses API, for the models that serve it. For most tasks, use Chat Completions.

Documentation menu

Create a response

curl "$CCSIO_BASE_URL/responses" \
  -H "Authorization: Bearer $CCSIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-responses-model",
    "instructions": "Answer in one short sentence.",
    "input": "What is an API gateway?"
  }'

input is a string or a list of input items; instructions is prepended as the system prompt. With "stream": true the answer is a stream of event-named server-sent events.

What is different from OpenAI

  • The answer carries text output only: tool calls and reasoning items of the model do not come back. For tools, use Chat completions.
  • The platform stores no response: store, previous_response_id and background are passed on but have no effect. Send the context you need in input.
  • status is completed, or incomplete with incomplete_details.reason when the model stopped early (for example at max_output_tokens).
Explore the platform

Get your first API key

Registration is open. Four steps to your first call: create your account, create your organization, create your API key, and start using it.

  1. 01Create your account
  2. 02Create your organization
  3. 03Create your API key
  4. 04Start using it