Stream Message

POST/chat/stream

Send a message with streaming response. Tokens are sent as they are generated.

No parameters for this endpoint.

Request Body

Same as Send Message — all fields are identical.

Field	Type	Required	Description
`agent_id`	string	Yes	Target agent ID (`ag_*`)
`message`	string	Yes	User message text
`session_id`	string	No	Session ID for conversation memory

Response — Server-Sent Events (SSE)

The response is a stream of text/event-stream events. Each event is a JSON object on a data: line:

data: {"type": "text", "content": "Machine learning is"}
data: {"type": "text", "content": " a subset of artificial intelligence"}
data: {"type": "text", "content": " that enables systems to learn"}
data: {"type": "tool_call", "name": "web_search", "args": {"query": "ML applications 2026"}}
data: {"type": "tool_result", "name": "web_search", "result": "..."}
data: {"type": "text", "content": " from data without being explicitly programmed."}
data: {"type": "done", "usage": {"input_tokens": 50, "output_tokens": 120, "total_tokens": 170}}

Event Types

Type	Fields	Description
`text`	`content`	Partial text chunk — concatenate all chunks for the full response
`tool_call`	`name`, `args`	Agent is invoking a tool
`tool_result`	`name`, `result`	Tool execution result
`done`	`usage`	Stream complete — includes final token usage
`error`	`message`	Error during generation

Client Example — JavaScript

const response = await fetch('https://api.thinnest.ai/chat/stream', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_TOKEN',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    agent_id: 'ag_c47e7c97_b2f2',
    message: 'Hello',
  }),
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;

  const text = decoder.decode(value);
  for (const line of text.split('\n')) {
    if (line.startsWith('data: ')) {
      const event = JSON.parse(line.slice(6));
      if (event.type === 'text') {
        process.stdout.write(event.content);
      }
    }
  }
}

Client Example — Python

import httpx
import json

with httpx.stream("POST", "https://api.thinnest.ai/chat/stream",
    headers={"Authorization": "Bearer YOUR_TOKEN"},
    json={"agent_id": "ag_c47e7c97_b2f2", "message": "Hello"}
) as response:
    for line in response.iter_lines():
        if line.startswith("data: "):
            event = json.loads(line[6:])
            if event["type"] == "text":
                print(event["content"], end="", flush=True)

Errors

Code	Description
`401`	Missing or invalid authentication
`402`	Insufficient balance
`404`	Agent not found
`429`	Rate limit exceeded