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 and set a spending cap, run it, then read the graded results and exports.
A run charges recorded usage against workspace credit. With a spending cap, new work stops when the cap or your balance can't fund the next call; calls already running finish and are charged. Finished work stays available.
Start here#
- Run your first evaluation from the CLI.
- Use the Python SDK, the TypeScript SDK or the model API from code.
- Bring your own benchmark from a file or a Hugging Face dataset, where your deployment has private imports.
Model compatibility explains which combinations run. Quotes and billing explains spending caps, credit set aside for running work, and charges.