Skip to main content
Standard Plan required. The Chatbase API v2 is available starting from the Standard Plan. View pricing →

Overview

The Chatbase REST API enables you to integrate AI-powered conversations into any application or workflow. Build custom chat experiences, automate customer interactions, and manage your AI agents programmatically. API v2 features structured error codes, cursor-based pagination, and real-time streaming via Server-Sent Events (SSE). Base URL:

Send Messages

Chat with your AI agents and handle real-time streaming responses

Manage AI Agents

Create, configure, and update AI agents and their training sources

Access Data

Retrieve conversations and messages from your AI interactions

Quick Start

1

Get Your API Key

Creating API key in Chatbase dashboard
  1. Visit your Chatbase Dashboard
  2. Go to Workspace settings → API keys
  3. Click Create API Key and copy the generated key
Store your API key securely and never expose it in client-side code.
2

Get Your Agent ID

Finding Agent ID in Chatbase settings
  1. Select your AI Agent in the dashboard
  2. Go to Settings → General
  3. Copy the Agent ID from the Agent details card
3

Send Your First Message

Test your integration with a simple chat request:
Expected Response:
stream defaults to true in API v2. Set it to false to receive the complete message as a single JSON response.
4

Continue the Conversation

Conversation history is stored by Chatbase — you don’t need to resend previous messages. Pass the conversationId from the previous response to send a follow-up:
To associate a new conversation with one of your users, pass a userId on the first message. See User Conversations for details.

Chat API Streaming

The chat API streams responses in real time using Server-Sent Events. Each event is a data: line containing a JSON object with a type field, and the stream ends with data: [DONE]. Concatenate the text-delta events to build the full reply, and read the conversationId from the finish event to continue the conversation.
For the full list of stream events — including client action (tool call) events — see the Streaming guide.

Error Handling

API v2 returns structured errors with a machine-readable code:
Every response includes an x-request-id header — include it when contacting support. See Error Handling for all error codes and Rate Limiting for limits and retry guidance.

Performance Best Practices

Optimization Strategies:
  • Use streaming for chat responses to improve perceived performance
  • Reuse conversationId for follow-ups instead of starting new conversations
  • Cache AI agent responses when appropriate
  • Respect the Retry-After header when you receive a 429 response
  • Use cursor-based pagination when listing conversations, messages, or sources

🚀 Try It Live!

Ready to see the magic in action? Dive straight into our interactive playground where you can test every API endpoint, experiment with real responses, and build your integration in real-time.

🎮 Launch Interactive Playground

Test APIs instantly • No setup required • Real-time responses • Copy working code snippets

Key API Endpoints

Chat API

Send messages and receive AI responses with streaming support

AI Agent Management

Create, update, and configure AI agents programmatically

Conversations

Access chat history and conversation messages

Sources

Add and manage the training sources for your AI agents

API v2 Overview

Explore the full API v2 reference — authentication, streaming, client actions, pagination, and more