Inference partners

Serve your users without watching them.

If you are moving real volume, we will meet you on rates and give you the same API everyone else gets. Your users stay anonymous to us, and your prompts stay yours.

We use this to reply to you, nothing else.

What happens next

  1. 1

    We read it

    A person, not a queue. We look at what you are building and what you need to serve it.

  2. 2

    We reply within two business days

    Either with terms, or with the questions we need answered before we can put terms together.

  3. 3

    You get a key

    The same OpenAI-compatible API everyone else uses. Point your base URL at us and keep your code.