Groq API Pricing
Groq runs open-weight models on custom LPU hardware, delivering some of the fastest inference speeds at low cost. Token Prices tracks Groq token pricing across Llama, Mixtral, and Gemma models.
Prices are per 1 million tokens and updated daily from the official Groq pricing page. View full Groq dashboard →
| Model | Input / 1M tokens | Output / 1M tokens | Context | Updated |
|---|---|---|---|---|
| llama-3.1-8b-instant | $0.05 | $0.08 | 128K | 2026-06-16 |
| llama-3.3-70b-versatile | $0.59 | $0.79 | 128K | 2026-06-16 |
| meta-llama/llama-4-scout-17b-16e-instruct | $0.11 | $0.34 | 128K | 2026-06-16 |
| moonshotai/kimi-k2-instruct-0905 | $1.00 | $3.00 | — | 2026-06-16 |
| openai/gpt-oss-120b | $0.15 | $0.6 | — | 2026-06-16 |
| openai/gpt-oss-20b | $0.075 | $0.3 | — | 2026-06-16 |
| qwen/qwen3-32b | $0.29 | $0.59 | 131K | 2026-06-16 |