Reference

API Reference

The BRICQS REST API. All endpoints return JSON. Authentication is via Bearer token obtained from POST /auth/login.

Base URL
https://api.bricqsai.com
CLIENTcurl / SDK / browserBearer tokenHTTPSAPI GATEWAYauth · rate limitapi.bricqsai.comrouteRUNTIMELLM · GPU · AgentContainer AppstreamRESPONSEJSON · SSE streamOpenAI-compatAll traffic is TLS-encrypted · audit-logged · rate-limited per token

Authentication

All endpoints (except /health and /status) require an Authorization header:

Authorization: Bearer <access_token>

POST /auth/login

bashcurl -X POST https://api.bricqsai.com/auth/login \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com", "password": "your-password"}'
json{
  "access_token": "eyJ...",
  "refresh_token": "...",
  "token_type": "bearer",
  "expires_in": 900
}

Deployments

GET
/deployments/list
List your deployments. Optional ?environment= filter.
POST
/deployments/deploy
Create a new deployment.
GET
/deployments/{id}
Get a single deployment by ID.
POST
/deployments/{id}/stop
Stop a running deployment (scale to zero).
DELETE
/deployments/{id}
Permanently delete a deployment.
GET
/deployments/{id}/logs
Get container logs. ?lines=100
GET
/deployments/{id}/metrics
Real-time BRICQS metrics. ?hours=6
POST
/deployments/{id}/promote
Promote preview → production with zero downtime.
GET
/deployments/models
List the deployable model catalog.
GET
/deployments/summary
Aggregated stats: active count, GPU hours, failure rate.

Deploy request body

namestringrequired
Name for this deployment. Used to generate the BRICQS deployment name.
model_idstringrequired
A model ID from GET /deployments/models.
environment'production' | 'preview' | 'development'
Deployment environment.
min_replicasinteger
Minimum replicas. 0 = scale to zero when idle.
max_replicasinteger
Maximum replicas for auto-scaling.

Models / Runtimes

POST
/runtime/{project_id}/chat/completions
OpenAI-compatible LLM proxy for a project.
POST
/agent/run
Run a tool-using agent with up to 6 reasoning steps.
POST
/rag-project/query
Query a RAG-indexed document collection.
POST
/workflow/{project_id}/run
Run a multi-step AI workflow.

Platform

GET
/status
Public platform status. No auth required.
GET
/health
API health check. No auth required.
POST
/support/tickets
Submit a support ticket.

Errors

All errors return { "detail": "message" } with the appropriate HTTP status:

400Bad request — invalid parameters401Missing or invalid access token403Insufficient permissions (account disabled, not admin, etc.)404Resource not found409Conflict — e.g. duplicate deployment for environment500Internal server error — check logs