Reference
REST API endpoints, config schema quick reference, changelog, and support resources.
REST API
All endpoints are served on PORT (default 8080). Admin endpoints require the RTD_ADMIN_TOKEN bearer token.
| Method | Path | Auth | Description |
|---|---|---|---|
| GET | /health | none | Liveness probe — returns 200 when gateway is running |
| GET | /ready | none | Readiness probe — returns 200 when all backends are healthy |
| GET | /metrics | none | Prometheus metrics in text exposition format |
| POST | /v1/chat/completions | key/jwt | OpenAI-compatible chat completions (streaming supported) |
| POST | /v1/completions | key/jwt | Legacy text completions endpoint |
| POST | /v1/embeddings | key/jwt | Generate text embeddings |
| GET | /v1/models | key/jwt | List all available models across backends |
| GET | /admin/api-keys | admin | List all API keys (paginated) |
| POST | /admin/api-keys | admin | Create a new API key |
| DELETE | /admin/api-keys/:id | admin | Revoke an API key by ID |
| GET | /admin/backends | admin | List backend status and health |
| POST | /admin/backends/:name/reset | admin | Reset circuit breaker for a backend |
| GET | /admin/routes | admin | List all routing rules |
| PUT | /admin/config | admin | Hot-reload gateway config (experimental) |
Config Schema Quick Reference
Top-level keys of gateway.yaml:
| Key | Type | Description |
|---|---|---|
| gateway | object | Global gateway settings: auth, TLS, timeouts, observability |
| listeners | list | Port/protocol bindings. Each entry has name, port, protocol, tls |
| backends | list | LLM provider connections (or pools). name, type, config required |
| routes | list | Request matching rules. name, path, methods, backend required |
| policies | object | Cross-cutting policies: rateLimit, retry, circuitBreaker, contentPolicy |
For the full JSON Schema, run rtd-gateway schema --output json or visit the API reference.
Changelog
v2.0January 2025
- NewMulti-provider pool backend with latency and cost strategies
- NewContent policy engine with PII detection and custom webhooks
- NewOpenTelemetry distributed tracing support
- NewOAuth 2.0 / OIDC browser flow and session management
- NewToken-based rate limiting (per hour / per day)
- ImprovedReduced cold-start overhead by 40% with lazy backend initialisation
- ImprovedPrometheus metrics now include per-model cost_usd counter
- FixedCircuit breaker state not persisting across gateway restarts
- FixedStreaming responses occasionally dropped final chunk
v1.5September 2024
- NewGoogle Gemini and Meta Llama provider adapters
- NewJWKS caching with automatic key rotation
- ImprovedRetry backoff now supports jitter to avoid thundering herd
- FixedAzure OpenAI adapter did not forward deployment-level headers
v1.0May 2024
- NewInitial release with OpenAI, Anthropic, and Azure OpenAI support
- NewAPI key authentication and per-key rate limiting
- NewRound-robin and weighted load balancing
- NewPrometheus metrics and structured JSON logging
Support
Contact Us
Talk to our team about enterprise plans, MSAs, and custom deployments.
Pricing Plans
Compare Solo, Team, and Enterprise tiers and start a free trial.
Security
Penetration test results, SOC 2 report, and responsible disclosure.
Status Page
Live uptime and incident history for all RTD services.