Platform
GA
Proprietary
GroqCloud
Ultra-low-latency chat and audio
Release2024-02
Context—
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary
Overview
GroqCloud is a model in the Platform category from Groq. It was released in 2024-02. The vendor is based in US. Best for: Ultra-low-latency chat and audio.
Strengths
- Very high tokens/sec on LPU
- Whisper
- Cheap
Limits
- Limited model choice
- Limited long-context support
Specifications
| Vendor | Groq |
|---|---|
| Category | Platform |
| Release | 2024-02 |
| Status | GA |
| License | Proprietary |
| Commercial use | Not specified |
| Input modalities | Text, Image, Audio |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | No |
| API access | Yes |
| Pricing | Token-based |
| Confidence | High |
| Vendor country | US |
| Vendor type | Platform |
Pricing & hardware
Token-based
API-only: local GPU memory is not applicable. API access is available.