Custom model endpoint with user-provided base URL.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Custom model endpoint with user-provided base URL. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Custom Model uses non-token pricing (for example per request, per second, or per page). The provider cards above show the exact current rates for each provider.
Custom Model is served by OffRail through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Custom Model supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
Custom Model was released on January 1, 2024.