Groq pricing & review
Custom LPU silicon serving open models at hundreds of tokens/second: the speed king for latency-sensitive apps, with simple per-token pricing.
Where Groq wins
- Fastest tokens/sec in the market
- Simple pricing
- Generous free tier for prototyping
Groq model pricing
List prices refreshed 2026-08-23 ยท cheapest 25 shown| Model | Input $/1M | Output $/1M | Market floor in |
|---|---|---|---|
| Gemma-7b-It | $0.050 | $0.080 | $0.050at Groq |
| GPT-OSS 20B | $0.075 | $0.300 | $0.015at Darkbloom |
| GPT-OSS-Safeguard-20b | $0.075 | $0.300 | $0.070at AWS Bedrock |
| Llama 4 Scout | $0.110 | $0.340 | $0.050at Lambda |
| GPT-OSS 120B | $0.150 | $0.600 | $0.050at DeepInfra |
| Llama 4 Maverick | $0.200 | $0.600 | $0.050at Lambda |
| Llama Guard 4 12B | $0.200 | $0.200 | $0.180at DeepInfra |
| Qwen3 32B | $0.290 | $0.590 | $0.050at Lambda |
| Qwen3.6 27B | $0.600 | $3.00 | $0.150at Libertai |
| Kimi K2 | $1.00 | $3.00 | $0.500at DeepInfra |