LiteLLM TypeSafe pass-through
If you already run LiteLLM as a proxy, this forwards the decision endpoint through it: clients hold a virtual key, the real key stays in the proxy environment, and usage is counted like any other model. The same page documents using Jev as the chooser inside LiteLLM's auto-router, which is a neat fit for a model whose output is already a choice.
- litellm
- proxy
- cost-tracking
- routing
- From
- BerriAI (LiteLLM) (US)
- Published
- 2026-09
- Listed here
- 2026-09-26
Sources checked
Also in this category
Gateways & access- Gateways & access
Jev on Vercel AI Gateway
A route to the model that does not need a TypeSafe account of your own: the gateway exposes Jev under its own model id, and the AI SDK calls it through a dedicated evaluate function rather than a chat completion. The gateway lists the model id typesafe-ai/jev and the same published input price as TypeSafe. Worth knowing about, because one of the independent evaluations listed here — the out-of-distribution calibration test — ran its calls through it.
Vercel2026-09-16
