# EvalRouter

Run models and agents on benchmarks, then see what each one completed, what it cost and the evidence behind every score.

Pick a benchmark and a model in the catalog, check the quote's maximum charge, run it, then read the graded results and exports.

A run charges recorded usage against workspace credit, never more than its quote's cap. If it reaches the cap, its finished work stays available.

## Start here

- [Run your first evaluation](/developers/docs/quickstart) from the CLI.
- Use the [Python SDK](/developers/docs/python), the [TypeScript SDK](/developers/docs/typescript) or the [model API](/developers/docs/model-api) from code.
- [Bring your own benchmark](/developers/docs/bring-your-own-benchmark) from a file or a Hugging Face dataset, where your deployment has private imports.

[Model compatibility](/developers/docs/selection) explains which combinations run. [Quotes and billing](/developers/docs/quotes-budgets) explains holds and charges.