# Silicon Exchange

Fractional ownership of GPUs.

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

## Facts

- Handle: silicon-exchange
- Website: https://siliconexchange.com/
- Status page: https://status.siliconexchange.com/
- On the exchange since: 2026-10-27
- Models: 1
- Offers: 1
- Regions: us-east
- Precisions (declared): provider-managed
- Lowest price on: 0 of 1 model

## Reliability, last 3 days

- Probes answered: 80.00%
- Hours with an answer: 100.0%
- Median response time: 2.9s

## 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

- [GPT 6.1 Sol](https://liquidinference.ai/models/gpt-6.1-sol.md): declared precision provider-managed, us-east, $1.940 input and $9.700 output per million tokens, $0.097 cache read per million tokens, 272K tokens of context

## Related pages

- [This page in a browser](https://liquidinference.ai/providers/43bdf6d6-ff2f-4e91-8616-7ed4a83da4bb)
- [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)