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: declared precision fp8, us-east, $0.050 input and $0.200 output per million tokens, $0.010 cache read per million tokens, 393.2K tokens of context