Create model response

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params

Creates a model response using the same interface as the OpenAI Create a model response API. Provide a text input string to generate text or JSON outputs. Supports non-streaming JSON and Server-Sent Events when stream=true.

Request – Requires model and input. All other request fields (tools, stream, temperature, instructions, and others) are provider-dependent — availability and semantics vary by the upstream provider selected via the model prefix. Consult that provider's documentation:

model uses the provider/model identifier format (e.g. openai/gpt-4o-mini, anthropic/claude-sonnet-4-20250514, gemini/gemini-2.5-flash), consistent with other AI Gateway endpoints.

input – A string (shorthand for a user message).

string
required
string
required
Headers
string
enum
Defaults to application/json
Allowed:
Responses

output items (messages, function calls, etc.).
  • Streaming: text/event-stream with data: SSE chunks.
  • Language
    Credentials
    Bearer
    LoadingLoading…
    Response
    Click Try It! to start a request and see the response here! Or choose an example:
    application/json
    text/event-stream