Developer portal

Build on think2earn Chat at chat.think2earn.com. The product is an agentic coding platform: long-running agents, artifacts, optional hosted apps, and the same credits for engineer handoff when you want a human on the thread.

REST / OpenAI-compatible API

• Base URL: https://chat.think2earn.com
• OpenAPI 3: /openapi.json
• Health: GET /api/health (no auth)
• Models: GET /v1/models
• Chat: POST /v1/chat/completions (streaming supported)

Authenticate with Authorization: Bearer t2e_…. Create API keys in the web app under Settings → API keys while signed in.

GraphQL

POST https://chat.think2earn.com/graphql — API key or OAuth. Schema introspection requires authentication.

MCP (Model Context Protocol)

Live Streamable HTTP MCP: POST https://chat.think2earn.com/mcp (JSON-RPC initialize, then tools/list). Discovery: /.well-known/mcp. Local stdio remains available via npm @cig-chat/mcp.

CLI

Official Python CLI on PyPI: chat-cli — script interactions without building a full HTTP client.

Rate limits

All /v1 responses include RFC 9239 headers:

• RateLimit-Limit — max requests in the window
• RateLimit-Remaining — requests left
• RateLimit-Reset — Unix epoch when the window resets

When throttled you receive HTTP 429 with Retry-After (seconds) and JSON:

{
  "error": { "message": "...", "type": "rate_limit_error", "code": "rate_limit_exceeded" },
  "code": "RATE_LIMITED"
}

More

llms.txt · About · Contact · Pricing