Platform
GA
Proprietary
Cerebras Inference
Very high tokens-per-second inference
Release2024-08
Context—
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary
Overview
Cerebras Inference is a model in the Platform category from Cerebras. It was released in 2024-08. The vendor is based in US. Best for: Very high tokens-per-second inference.
Notes: Positioning from the vendor site; specs, access and pricing can change — verify before production use.
Strengths
- Wafer-scale speed
- Low latency
- Open model hosting
Limits
- Limited model catalog
- Closed platform
Specifications
| Vendor | Cerebras |
|---|---|
| Category | Platform |
| Release | 2024-08 |
| Status | GA |
| License | Proprietary |
| Commercial use | Not specified |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | No |
| API access | Yes |
| Pricing | Usage-based API |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Cloud provider |
Pricing & hardware
Usage-based API
API-only: local GPU memory is not applicable. API access is available.