Stable client API
OpenAI Chat, OpenAI Responses, Anthropic Messages, SDKs, Codex CLI, and Claude Code can call one governed endpoint.

Metrum AI Product Documentation
A deployable enterprise gateway that keeps GenAI clients stable while routing policy, provider keys, model selection, budgets, telemetry, and request-time cost accounting stay under platform control.
OpenAI Chat, OpenAI Responses, Anthropic Messages, SDKs, Codex CLI, and Claude Code can call one governed endpoint.
Expose quality and cost contracts instead of raw provider IDs, then tune providers and weights without client rewrites.
Tool, image, dialect, and max-token requirements filter targets before the router calls an upstream model.
Usage rows and reports preserve provider/model, tokens, image fields, cache, latency, attempts, fallbacks, and request-time cost.
Mix external providers with enterprise vLLM, SGLang, Baseten-style, or other OpenAI-compatible services behind one API.