Changelog
Changelog
v1 — Initial Release
Endpoints
POST /v1/chat/completions— OpenAI-compatible chat completionsPOST /v1/responses— Stateful Responses APIPOST /v1/web-search— Web search with structured resultsPOST /v1/fetch— Extract text content from URLsGET /v1/models— List available models and pricingGET /v1/license— Check license info and credit balance
Providers
- OpenRouter — 300+ LLMs (default for chat completions, responses, models)
- Anthropic — Claude models directly
- Exa — Web search and content fetch (default)
- Tavily — Web search and content fetch (alternative)
Features
- OpenAI SDK compatibility
- SSE streaming for chat completions and responses
- Unified credit billing across all providers
- JWT authentication with auto-provisioning
- Per-institution configuration
- Provider routing via
X-Quantized-Providerheader