Become a provider

Sell your inference capacity on Batchrouter

Serve large-volume async AI jobs from your own endpoint. Setup is self-serve and checked automatically — you can go live the same day.

Listed providers

—

Loading live figures

Models

—

Loading live figures

Executions

—

Loading live figures

Checking your account…

How it works

1
Register
~2 min
Tell us about your company and your endpoint. That's this form.
2
Set up in the portal
~10 min
A checklist walks you through it: add a model and your price, test your endpoint, confirm capacity, add payout details.
3
Go live
when ready
Every check is automatic, with no manual review. Once the checklist is complete, press Go live and Batchrouter starts routing matching work to you automatically. You start with conservative limits that grow as you deliver.

What you'll need

A public https:// endpoint that serves the OpenAI Batch API, chat completions, or both, and the API key Batchrouter should use
The country or countries your inference runs in
How long you keep prompts and outputs
For the portal, after you register: the model IDs you serve and, per model, your prices per 1M tokens, plus where to send payouts