Models, usage and limits

Different models suit different tasks; speed, quality, context length, tool support and price vary. The picker shows what each model supports, and you can switch models within a conversation.

Some models are free to use. Their availability depends on the companies that run them, and they can have their own limits on how often you can use them.

Each account has a monthly usage budget. A request reserves part of it while it runs and is then charged at its actual cost; a request that fails before it starts costs nothing. When the budget is used up, new requests pause until it renews.

Settings → Usage shows what you have spent this month and over time.

Your message, the context it needs and any files you attach go to the company that runs the model you chose. Entevra asks for providers that do not collect your data, and Entevra does not train models on your content.