Groq
Groq builds the LPU, its own inference chip, and runs GroqCloud, which sells open models per token with published speeds. Its data centres are in the United States and, since 2025, Dammam in Saudi Arabia with Aramco Digital; the price list names no region.
- Website: https://groq.com
- Headquarters: Mountain View, United States
- Kind: Inference provider, Per-token API
Groq sells 3 of the compared models per token and prices 0 kinds of GPU for hosting your own.
Models sold per token
| Model | Input, per 1M tokens | Output, per 1M tokens |
|---|---|---|
| OpenAI gpt-oss 120B | $0.15 | $0.60 |
| OpenAI gpt-oss 20B | $0.075 | $0.30 |
| Qwen3.8 27B | $0.80 | $4.00 |
Where it runs
One global price; Groq chooses where a request is processed.
No place stated for 3 models: one global price, and Groq does not say where a request is processed.
Where the prices come from
- Per-token prices: console.groq.com/docs/models
Sources
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.