# Base models

Every Task starts from an open base model, and Facet builds your version on top of it. Facet picks the base when it drafts the Task; you can change it on the draft under **Base model**.

| Base model | Best for | Input, per 1M tokens | Output, per 1M tokens |
|---|---|---|---|
| Qwen3.5 0.8B | Simple, high-volume jobs: short labels, routing, yes or no | $0.04 | $0.12 |
| Qwen3.5 4B | Most Tasks: extraction, rewriting, judgment calls (the default) | $0.08 | $0.25 |


Both are Qwen3.5, from Alibaba's Qwen team, under the Apache 2.0 license, so an exported Task runs anywhere. See [Limits](/docs/limits) for the longest input each takes.

## Which to pick

- **Start with the default.** It handles most Tasks well.
- **Try the smaller one** when answers are short and the job is simple, such as a label from a short list, and you make many calls. It costs about half as much per token.
- Compare them on your own Expectations: make the same Task twice and read both scorecards.

## What stays the same

A version records the exact revision of its base, so it answers the same way until you change it. When Facet retires a base, Tasks on it keep their history and exports but stop answering calls; move one by making a new Task on a current base.

## Next steps

- [Pricing](/docs/pricing): what building and calling a Task costs
- [Export your model](/docs/export): run a Task on your own hardware