Agents: this page is also Markdown; every page is in llms.txt.
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 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: what building and calling a Task costs
- Export your model: run a Task on your own hardware