# Models

> Find a model, compare its price and limits, and copy a setup for your tool.

[Models](https://deference.si/models) is public. Browse it without signing in, then use a model's full id in your tool or API request.

## Find a model for your request

Search by name, id or maker. Use the maker bar to narrow the list, and **Capabilities** to choose Reasoning, Tools, Vision, Images or Embeddings. **+N** opens the remaining makers.

Each row shows the context window and input and output prices per million tokens. Sort by Featured, Newest, Cheapest or Longest context. Popular is available when Deference has enough usage to rank models.

Select **Copy** to copy a model id, or open the row to check the model in more detail. The list starts with 40 rows; **Show all** displays the rest.

Filters stay in the URL. For example, `/models?type=embeddings&provider=openai` shows OpenAI embedding models. See [Choose a model](https://deference.si/docs/models) for endpoint selection and all capability filters.

## Check the price and limits

On a model's page, check its input and output prices, context window and supported capabilities. Prices include OpenRouter's 5% platform fee. Deference adds no markup.

Use the limits published for the model when a coding tool asks for them. A model must support the capability your request needs, such as vision or tool calling.

## Connect your tool

Use **Copy model ID** for the exact id, or choose a tool under **Set up in** to copy settings with that id filled in. The page includes setups for Claude Code, Codex, Cursor, OpenCode, curl and Python.

For a complete walkthrough, open the relevant [coding tool guide](https://deference.si/docs/coding-tools). To send requests from your own code, see [API overview](https://deference.si/docs/api-reference).

Press / to search, Escape to clear the search, and J or K to move between rows.