# Corvex

Token Factory: Security-first serverless inference for GLM 5.3 and DeepSeek V4 Flash 0731 on Corvex-owned U.S. GPUs. Zero Data Retention; no training.

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

## Facts

- Handle: corvex
- Website: https://corvex.ai/
- Terms of service: https://www.corvex.ai/terms-of-use
- Privacy policy: https://www.corvex.ai/privacy-policy
- On the exchange since: 2026-10-26
- Models: 1
- Offers: 1
- Regions: us-east
- Precisions (declared): fp8
- Lowest price on: 0 of 1 model

## Reliability, last 3 days

- Probes answered: 100.00%
- Hours with an answer: 100.0%
- Median response time: 13.2s

## 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
- SOC 2 Type II, declared by the provider
- SOC 2 Type I, declared by the provider
- HIPAA BAA, declared by the provider

## Models

- [GLM 5.3](https://liquidinference.ai/models/glm-5.3.md): declared precision fp8, us-east, $0.100 input and $0.100 output per million tokens, $0.010 cache read per million tokens, 393.2K tokens of context

## Related pages

- [This page in a browser](https://liquidinference.ai/providers/aa9d3020-1f34-4522-97ed-1c6863f4fdba)
- [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)