# Model Router: your keys, every provider

> Model Router now takes your own key for each of 13 providers it can route to, blocks models by org policy, and shows ROI over the same window as your spend.

Source: https://entelligence.ai/changelog/2026-08-24-model-router-keys-for-every-provider
Updated: 2026-08-24

Aug 24, 2026 · Model Router

Bring a key for each provider your organization already pays, and Model Router routes through it. When none of your keys serves the model it picks, the turn runs on your Entelligence credits. A model policy keeps blocked models out of every route.

## A key per provider, edited one at a time

Model Router offers a slot for each of the 13 providers it can actually route to, and each slot is edited on its own, so adding a fifth key never touches the other four. A card says plainly when a provider is accepted but not yet routable. Keys can be added after onboarding, and a hybrid mode falls back to managed capacity when your own key cannot serve a request.

## An org model policy

Block a model for the whole organization and it leaves every routing tier, whichever key would have served it. The provider list comes from the same registry the router reads, so the settings page and the router can never disagree about what is available.

## ROI and usage, over the same window

A new ROI tab compares routed cost with what the same work would have cost sent direct, over the same window as the rest of the dashboard. Usage-over-time charts show router-scoped spend with full token columns, and `router stats` in the CLI now leads with your most recent session.

## Improvements

- Model Router: Choose the auto top-up amount and the balance floor that triggers it.
- Model Router: OpenRouter, Azure AI Foundry and Fireworks AI as bring-your-own-key providers.
- Model Router: Org members, not only admins, can view the router dashboard.
- Model Router: Each conversation gets its own prompt cache.
- CLI: The router daemon runs on Windows.

## Fixes

- Model Router: Auto top-up charges the saved card as intended.
- Model Router: Savings are no longer floored per row, so the two dashboard pages agree.
- Model Router: The daily cache-hit rate can no longer exceed 100%.
- Model Router: The Sessions and Members tabs honour the range picker.
- CLI: `router on` always works for organizations on their own keys.

## Read more

- [Model Router](https://entelligence.ai/model-router)
- [Ellie CLI](https://entelligence.ai/cli)

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