# Butler

We serve cheap, fast, and private inference from our proprietary distributed inference network across the U.S.

Butler sells inference on Liquid Inference. A buyer names one of its models as butler/\<model\>, or names the model and pays the lowest offer that meets the buyer's rules.

## Facts

- Handle: butler
- Website: https://butlercompute.com/
- Terms of service: https://butlercompute.com/terms/
- Privacy policy: https://butlercompute.com/privacy/
- On the exchange since: 2026-10-30
- Models: 1
- Offers: 1
- Regions: us-east
- Precisions (declared): nvfp4

## Reliability, last 3 days

- Probes answered: 100.00%
- Hours with an answer: 100.0%
- Median response time: 196ms

## Checked by the exchange

0 of 1 offer matches the fingerprint of the model. 0 have a finished evaluation.

The exchange sends fixed prompts to each offer and compares the answers with a baseline for the model. It also runs benchmarks against the offers and keeps the results.

## Data handling

- Zero retention, declared by the provider
- No training, declared by the provider

## Models

- [Cicero](https://liquidinference.ai/models/cicero.md): declared precision nvfp4, us-east, $0.020 input and — output per million tokens, $0.010 cache read per million tokens, 32.8K tokens of context

## Related pages

- [This page in a browser](https://liquidinference.ai/providers/d67876a0-a216-4a7c-9ab7-69c142683ee2)
- [All providers](https://liquidinference.ai/providers.md)
- [All models](https://liquidinference.ai/models)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)