Axiomancer

RouteShift

An LLM proxy gateway that turns every request into a routing decision — pick the best model, fail over to the cheapest, and bill back the savings.

RouteShift analytics dashboard showing requests, actual spend, savings versus list price, model routing, and a recent request log
  • Point OpenAI-compatible clients at https://api.routeshift.io/v1.
  • Use deployed chat completions, embeddings, models, and model-detail routes.
  • Review routing behavior, token use, cost, and activity in one place.
Product preview
Proxy analytics put spend, savings, model routing, and recent request behavior in one view.

Get started

Sign up, mint your first key, and proxy your first request.

Marketing site

Pricing, providers, and the savings-share model.

How a request flows

RouteShift exposes an OpenAI-compatible client surface at https://api.routeshift.io/v1. The deployed public routes cover chat completions, embeddings, models, and model detail.

  1. Send a request

    Use an OpenAI-compatible client against the public base URL.

  2. Authenticate

    RouteShift applies the virtual key and its configured limits.

  3. Route

    Rules select an available model or configured fallback path.

  4. Return and observe

    The response returns while token, cost, and activity data are recorded.

Every request is authenticated, routed against your rules, and the response is logged and costed on its way back to your app.

What RouteShift covers

  • Virtual API keys — sk-proxy- keys with per-key allowed models, RPM/TPM limits, monthly budgets, expiry, metadata tags, rotation with grace periods, and a full audit trail.
  • Routing & fallbacks — rules that pick a target model (or a chain), with model aliases, weighted load balancing across N provider keys, latency-based and least-busy strategies, and automatic 5xx/429 cooldowns.
  • Observability — every request is logged with tokens, cost, latency, and an inferred activity category. Sessions are stitched together for one-shot vs. retry-rate analysis and side-by-side model comparison.
  • Optimize findings — a static-analysis pass over recent traffic that flags duplicate prompts, oversized system prompts, model-mismatch waste, and other cost leaks.
  • Spend & savings — pricing pulled directly from the LiteLLM JSON catalog, monthly per-key budgets with projected-overrun alerts, per-key cost attribution in the billing breakdown, and a 3% savings-share monetization model.

BYOK is the default: you bring provider keys, RouteShift never resells inference.

RouteShift ships weekly — follow release notes in the changelog.

Was this page helpful?

Get started with RouteShift

Sign up for RouteShift, add a provider, mint a virtual key, and proxy your first request — ship a routed LLM call against any model in under ten minutes.

On this page

How a request flowsWhat RouteShift covers