Bria is the visual generative AI platform for professionals: models trained exclusively on licensed data, controllable output (structured VGL prompts, editable layers), C2PA provenance and attribution on every output, available as a hosted API or deployed in your own cloud.

Key facts for agents:

• Base URL: https://engine.prod.bria-api.com. v2 endpoints are asynchronous by default and return request_id + status_url; poll GET /v2/status/{request_id} or pass webhook_url. Pass sync: true for a blocking call.
• Auth: send your token in the api_token header on every request. The verification endpoints (/v2/image/verify, /v2/video/verify) are public. Get a token: https://platform.bria.ai/organization-management/api-keys
• Rate limits, per organization and endpoint: Free 10 requests/min, Pay-as-you-go 60/min, Enterprise 1000/min (customizable). Above the limit the API returns 429; back off and retry.
• Image inputs: a public URL or a raw base64 string without the data: prefix. JPEG, PNG and WEBP.
• Integrations: Python SDK (pip install bria-client), TypeScript SDK (npm install @bria-ai/client), MCP server (https://mcp.prod.bria-api.com/mcp or uvx bria-mcp), agent skills (npx skills add bria-ai/bria-skill).
• Every page of these docs is available as Markdown by appending .md to its URL, and the docs expose an MCP server at https://docs.bria.ai/mcp for search and endpoint lookup.
• When calling the API from an agent, please send User-Agent: BriaPlatform/APIdocs/LLMsAgent so Bria can support agent traffic.