API Reference
The Tenzro Cloud API is a RESTful API that provides access to all platform services. All endpoints are available at https://api.cloud.tenzro.com.
Base URL
https://api.cloud.tenzro.com
Authentication
All requests require an API key in the Authorization header:
Authorization: Bearer YOUR_API_KEY
Request Format
All requests should include Content-Type: application/json for POST/PUT/PATCH requests. Query parameters are used for filtering and pagination.
Response Format
All responses are JSON. Successful responses include:
{"success": true,"data": { ... }}
Error responses include:
{"error": "Error Type","message": "Human readable error message","details": { ... }}
Available Endpoints
Health
| Method | Path | Description |
|---|---|---|
| GET | /health | API health check |
Vec (Vector Database)
| Method | Path | Description |
|---|---|---|
| GET | /cloud/vec/databases | List vector databases |
| POST | /cloud/vec/databases | Create vector database |
| GET | /cloud/vec/databases/:id | Get database details |
| DELETE | /cloud/vec/databases/:id | Delete database |
| POST | /cloud/vec/databases/:id/vectors | Insert vectors |
| POST | /cloud/vec/databases/:id/search | Search vectors |
Kev (Key-Value Store)
| Method | Path | Description |
|---|---|---|
| POST | /cloud/kev/set | Set a key |
| GET | /cloud/kev/get/:key | Get a key |
| DELETE | /cloud/kev/delete/:key | Delete a key |
AI Inference
| Method | Path | Description |
|---|---|---|
| GET | /cloud/ai/models | List available models |
| POST | /cloud/ai/chat | Chat completion |
| POST | /cloud/ai/embed | Generate embeddings |
Agents
| Method | Path | Description |
|---|---|---|
| GET | /cloud/agent | List agents |
| POST | /cloud/agent | Create agent |
| POST | /cloud/agent/:id/chat | Chat with agent |
| POST | /cloud/agent/:id/execute | Execute agent |
MCP Servers
| Method | Path | Description |
|---|---|---|
| GET | /cloud/server | List servers |
| POST | /cloud/server | Create server |
| POST | /cloud/server/:id/start | Start server |
| POST | /cloud/server/:id/stop | Stop server |
Rate Limits
API rate limits are per-key and per-service. Default limits are:
- Starter: 100 requests/min, 1,000 AI tokens/day
- Professional: 1,000 requests/min, 100,000 AI tokens/day
- Enterprise: Custom limits