Chat API

Send messages to AI agents and receive streaming responses.

Send Message

POST /v1/chat/completions

Scope required: chat

Request Body

{
  "message": "I need help with my invoice",
  "space": "soporte",
  "chat_id": "optional-existing-chat-id"
}

Field	Type	Required	Description
message	string	✅	The user's message
space	string	❌	Space code or ID. Uses API key's default or first space
chat_id	string	❌	Continue an existing conversation

Response (SSE Stream)

The response is a Server-Sent Events stream:

data: {"text": "Hello"}

data: {"text": "! How can"}

data: {"text": " I help you?"}

data: [DONE]

Event Types

Event	Description
{"text": "..."}	Text token (streaming)
{"type": "agent_info", "agent_id": "..."}	Which agent was selected by the router
{"type": "system_alert", "data": {...}}	Action execution notification
{"type": "component", "component_name": "...", "props": {...}}	Generative UI widget
[DONE]	Stream complete

cURL Example

curl -N -X POST https://senda.telar.ai/api/v1/chat/completions \
  -H "Authorization: Bearer sk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message": "What are your business hours?", "space": "soporte"}'

JavaScript Example

const res = await fetch('https://senda.telar.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk_live_YOUR_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({ message: 'Hello', space: 'soporte' })
});

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

while (true) {
  const { value, done } = await reader.read();
  if (done) break;
  const text = decoder.decode(value);
  // Parse SSE events
  for (const line of text.split('\n\n')) {
    if (line.startsWith('data: ') && line !== 'data: [DONE]') {
      const data = JSON.parse(line.slice(6));
      if (data.text) process.stdout.write(data.text);
    }
  }
}

Chat History

GET /v1/chat/history/:chatId

Returns the full message history for a chat session.

Response

{
  "chat_id": "chat_abc123",
  "messages": [
    {
      "id": "msg_1",
      "role": "user",
      "content": "Hello",
      "created_at": "2026-05-07T12:00:00Z"
    },
    {
      "id": "msg_2",
      "role": "agent",
      "content": "Hi! How can I help?",
      "agent_id": "agent_soporte",
      "created_at": "2026-05-07T12:00:01Z"
    }
  ]
}