Browse the Model Catalog
The Model Catalog lists every model available through Serverless Inference. Use it to find the right model and note its name for your API requests.
Open the Model Catalog
In the left sidebar under Serverless Inference, click Models.
Read a model card
Each card in the catalog shows:
| Field | Description |
|---|---|
| Model name | The name to pass as the model parameter in API requests |
| Provider | The organization that published the model (e.g. Meta, Mistral AI, Google) |
| Context window | Maximum number of tokens the model can process in a single request (input + output combined) |
| Input price | Cost per 1 million input (prompt) tokens |
| Output price | Cost per 1 million output (completion) tokens |
Filter and search
Use the search bar above the catalog to filter by model name or provider. Click a model card to open its detail view with the full model description and gateway URL.
What's next
- Create an API Key — generate a key to authenticate your requests.
- Call the Inference API — make your first API call with the model you chose.