meta-llama API Pricing
All 15 meta-llama models by input price. Refreshed hourly.
| Model | Input /1M | Output /1M | Blended | Context | Intelligence | CPS | |
|---|---|---|---|---|---|---|---|
| Meta: Llama 4 Maverick | $0.19 | $0.65 | $0.30 | 524K | 9 | B | Details → |
| Meta: Llama 4 Scout | $0.10 | $0.30 | $0.15 | 1.3M | 7 | B | Details → |
| Llama Guard 3 8B | $0.48 | $0.03 | $0.37 | 131K | — | — | Details → |
| Meta: Llama Guard 4 12B | $0.18 | $0.18 | $0.18 | 164K | — | — | Details → |
| Meta: Llama 3.3 70B Instruct (free) | Free | Free | $0.00 | 131K | — | — | Details → |
| Meta: Llama Guard 4 12B (free) | Free | Free | $0.00 | 164K | — | — | Details → |
| Meta: Llama 3.2 11B Vision Instruct | $0.34 | $0.34 | $0.34 | 131K | — | — | Details → |
| Meta: Llama 3.2 3B Instruct | $0.05 | $0.34 | $0.12 | 131K | — | — | Details → |
| Meta: Llama 3.1 70B Instruct | $0.40 | $0.40 | $0.40 | 131K | — | — | Details → |
| Meta: Llama 3 70B Instruct | $0.51 | $0.74 | $0.57 | 8K | — | — | Details → |
| Meta: Llama 3 8B Instruct | $0.14 | $0.14 | $0.14 | 8K | — | — | Details → |
| Meta: Llama 3.2 1B Instruct | $0.03 | $0.20 | $0.07 | 60K | — | — | Details → |
| Meta: Llama 3.2 3B Instruct (free) | Free | Free | $0.00 | 131K | — | — | Details → |
| Meta: Llama 3.1 8B Instruct | $0.05 | $0.08 | $0.06 | 131K | — | — | Details → |
| Meta: Llama 3.3 70B Instruct | $0.10 | $0.32 | $0.15 | 131K | — | — | Details → |
FAQ
What is the cheapest meta-llama model?
By input price, Meta: Llama 4 Maverick is lowest ($0.19/1M tokens). See the full table above.
How is meta-llama priced?
Usage-based: input and output priced separately per 1M tokens, with cache read/write discounts on some models. The Blended column estimates a typical 3:1 request cost.