Groq API pricing
Open-weight models on custom LPU hardware, delivering some of the fastest inference speeds at low cost.
| Model | Input per 1M tokens | Output per 1M tokens |
|---|---|---|
| llama-3.1-8b-instant | $0.0500 | $0.0800 |
| llama-3.3-70b-versatile | $0.5900 | $0.7900 |
| moonshotai/kimi-k2-instruct-0905 | $1.00 | $3.00 |
| openai/gpt-oss-120b | $0.1500 | $0.6000 |
| openai/gpt-oss-20b | $0.0750 | $0.3000 |
| qwen/qwen3.6-27b | $0.6000 | $3.00 |
Groq API Pricing
Open-weight models on custom LPU hardware, delivering some of the fastest inference speeds at low cost.
Prices are per 1 million tokens and updated daily from the official Groq pricing page. View full dashboard →
