Choosing a group

A group is a setting on an API key: it decides which line the key's requests use and which price tier they are billed at. Most models are offered in several groups, each with its own price and source. Calls look exactly the same in every group, so switching groups means switching keys, not code.

All groups

What the labels next to a group name mean:

One model, different prices per group

Live prices for the same model in each group — the gap can be several times:

The model hub shows each model's cheapest group by default; a model's own page lists its price in every group.

The key decides the group

• You pick the group when you create or edit an API key in the console. A key can use one group, or several groups in priority order (up to 5).
• With several groups, each request uses the first group in the order that offers the model, and is billed at the group actually used. With cross-group retry on, a request that still fails after its retry in the current group moves on to the next group. The switching rules and how to order groups are in LLM API high availability.
• A request cannot override the group. To change groups, edit the key's groups in the console, or use another key.
• Groups do not all offer the same models. If none of a key's groups offers a model, the request returns 503 with the code model_not_found. Add a group that offers the model to the key, or check the model's page to see which groups have it.
• Calling the models endpoint with a key returns exactly the models that key can use.

How to choose

Before going live, send real requests with a key in the group you plan to use, and check quality, speed and the charges in Logs in the console (see Billing and usage) before you settle on a production group.