Cerebras
OperationalWafer-scale AI inference at record speeds
Ultra-fast inference powered by the world's largest AI chip.
Company
- Headquarters
- Coming soon
- Founded
- Coming soon
Capabilities
- Models Hosted
- Curated Deck
- Inference Speed
- 2000+ tokens/sec
- Specialties
- Coming soon
- Unique Features
- Wafer-scale chips
- API Style
- OpenAI-compatible
- Est. Compute Region
- US + Canada + EU [source]
Compute locations are estimated from public sources and may be outdated. Verify directly with the provider for compliance decisions.
Models
Coming soon
We are standardizing model listings across providers.
Why Use Cerebras
Coming soon
Details
Coming soon
Newsletter
Get the signal, skip the noise.
Weekly digest of new models and provider updates across 40+ compute providers. Curated for AI builders who ship.
New model releases
Capability updates
Provider status