Stream LLM Response (v2)

Send messages using OpenAI-compatible format and receive streaming responses.

Request Parameters

ParameterRequiredDescription
messagesYesArray of message objects with role and content
toolsNoArray of tool definitions for function calling

Message Format

Each message object must contain:

  • role: "user", "assistant", or "system"
  • content: The message text

Response Format

Returns a Server-Sent Events (SSE) stream with JSON objects containing:

  • status: "success" or "fail"
  • type: "message", "tool_call", or "finish"
  • content: The response content
  • role: The assistant's role

Example

Select "LLMV2Request" from the Examples dropdown to see the request format.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Path Params
string
required
Body Params
messages
array
required
messages*
tools
array
tools
Headers
string
enum
Defaults to application/json

Generated from available request content types

Allowed:
Responses
400

Bad Request - Invalid input data or parameters.

401

Unauthorized - Invalid or missing authentication credentials.

403

Forbidden - You do not have permission to perform this action.

404

Not Found - The requested resource could not be found.

405

Method Not Allowed - Invalid HTTP method

406

Not Acceptable - Invalid request accept headers

415

Unsupported Media Type - Invalid content type

500

Internal Server Error - An unexpected error occurred.

Language
LoadingLoading…
Response
Click Try It! to start a request and see the response here!