# Route each API request with model auto

> Send model "auto" to the Model Router and each API request is routed on its own content, across a curated catalog of 30 cheap, 23 mid and 32 frontier models.

Source: https://entelligence.ai/changelog/2026-10-16-model-auto
Updated: 2026-10-16

Oct 16, 2026 · Model Router

The Model Router now serves plain API traffic as well as coding agents. Set the model to "auto" on an OpenAI or Anthropic shaped request and the router picks the cheapest model that can handle that one request.

## One request, one decision

Coding agents keep a session: switching models mid-task throws away the prompt cache, so the router holds a session to its model until the work gets hard. An API caller has different needs. With "auto" (or "entelligence/auto"), each request gets its own decision, classified on its latest user message, and leaves no session state behind.

It works on both /v1/chat/completions and /v1/messages. Any other model name keeps the agent behaviour exactly as before.

## The answer says where it ran

Every response carries x-router-model with the model that served it and a new x-router-tier header with its tier. Failover, billing, bring-your-own-key and per-org policy run the same pipeline in both modes.

## A curated catalog, weighted to the cheapest capable model

The catalog keeps the latest two versions of each model line and retires the rest, which took out 100 registrations. What remains is 30 cheap, 23 mid and 32 frontier models, and tier weighting now favours the cheapest model that is capable of the request. Retired models still resolve for billing history and pinned sessions.

## Benchmarks refreshed every hour

Artificial Analysis metrics now load hourly, and the router added the 14 models and effort levels from the Artificial Analysis top 40 that it was missing, plus cost-per-task figures seeded from their model pages.

## Improvements

- Model Router: Members see their own sessions, savings and model quality.
- Model Router: Model usage and cost are listed with pagination.
- Model Router: The usage percentage explains that it counts tokens.
- Model Router: September models added with verified routing.

## Fixes

- Model Router: An inert bring-your-own-key fallback toggle is gone, and settings links point to the right pages.
- Model Router: The member view stays up when a panel fails, and savings show only what was measured.
- Model Router: Role copy on the router settings matches who can change them.

## Read more

- [Model Router](https://entelligence.ai/model-router)
- [Documentation](https://docs.entelligence.ai)

All releases: [Changelog](https://entelligence.ai/changelog.md)