Documentation
Overview
Models
One API for hundreds of models.
A4F strives to provide access to every potentially useful text-based AI model. We currently support over 300 models endpoints.
If there are models from specific original creators (e.g., from a new LLM company) or particular model variants that A4F doesn't yet offer access to through our provider network, please tell us about them in ourDiscord channel.
Different models tokenize text in different ways
Some models break up text into chunks of multiple characters (GPT, Claude, Llama, etc), while others tokenize by character (PaLM). This means that token counts (and therefore costs) will vary between models, even when inputs and outputs are the same. Costs are displayed and billed according to the tokenizer for the model in use. You can use the
usage field in the response to get the token counts for the input and output.Explore and browse 300+ models and providers on our website, or with our API.
For Providers
If you're interested in working with A4F, you can learn more on ourproviders page.
Was this page helpful?