Everything you need before hitting the endpoints below.
Base URL
All endpoints are prefixed with /v1.
Authentication
Sign in and go to Profile → API Keys to generate your key. Keys start with gb_sk_.
Include it in the Authorization header with every request:
Authorization: Bearer gb_sk_<your-key>
You can also use the X-API-Key header:
X-API-Key: gb_sk_<your-key>
Rate Limits
60 requests per minute.
Every response includes headers showing your current usage:
X-RateLimit-Limit-Minute: 60
X-RateLimit-Remaining-Minute: 59
X-RateLimit-Reset-Minute: 2026-01-07T13:21:00.000Z
When you exceed the limit, you’ll get a 429 response with a Retry-After header (seconds to wait).
All chat responses return analysis in the content field:
{
"session_id": "uuid",
"content": "The analysis or JSON data goes here",
"timestamp": "2026-01-07T12:00:00Z"
}
The response field is content (not message).
For structured data, add “Respond as JSON with:” to your query and specify the fields. The content field will contain parseable JSON instead of markdown.
Response Times
| Query Type | Typical Response Time |
|---|
| Simple data lookups (prices, funding rates, Fear & Greed) | 40-60 seconds |
| Multi-domain analysis (trade setups, protocol deep dives) | 60-120 seconds |
| Complex aggregations (yield opportunities, perp DEX rankings) | 120-180 seconds |
| Maximum timeout | ~600 seconds |
Set your HTTP client timeout to at least 600 seconds. If a query times out (504), break it into smaller, more specific requests.
HTTP Status Codes
| Status | Meaning |
|---|
200 | Success |
201 | Resource created |
400 | Bad request |
401 | Invalid or revoked API key |
404 | Resource not found |
429 | Rate limit exceeded |
500 | Server error |
504 | Query timeout (try a simpler query) |
Support
When contacting support, include:
- Your API key (first 10 characters only)
- Session ID from error responses