Llama (Meta) › Pricing
Llama API pricing
Meta · per 1M tokens · list prices from the lab · checked Oct 23, 2026
All Llama modelsclick a row for its full price sheet
| Model | Input | Output | Cache read | Context | Released ↓ | Status |
|---|---|---|---|---|---|---|
Muse Spark Open | h$1.25 | $4.25 | — | 1M | Oct 2026 | |
Muse Wonder | $4 | $20 | $0.20 | 1M | Oct 2026 | |
Muse Spark 1.3 | $1.25 | $4.25 | $0.15 | 1M | Sep 2026 | |
Muse Glimmer 30B | h$0.30 | $1.10 | — | 131K | Aug 2026 | |
Muse Spark 1.2 Older | $1.25 | $4.25 | $0.15 | 1M | Aug 2026 | Older |
Muse Spark 1.1 Older | $1.25 | $4.25 | $0.15 | 1M | Jul 2026 | Older |
Muse Spark Older | $1.25 | $4.25 | $0.15 | 1M | Apr 2026 | Older |
Llama Guard 4 12B | h$0.18 | $0.18 | — | 164K | Apr 2025 | |
Llama 4 Scout | h$0.10 | $0.30 | — | 10M | Apr 2025 | |
Llama 4 Maverick | h$0.19 | $0.65 | — | 1M | Apr 2025 | |
Llama 4 Maverick 17B 128E Instruct FP8 | h$0.20 | $0.80 | — | 1M | Apr 2025 | |
Llama 3.3 70B Instruct | h$0.10 | $0.32 | — | 128K | Nov 2024 | |
Llama 3.2 90B Vision Instruct | h$0.35 | $0.40 | — | 33K | Sep 2024 | |
Llama 3.2 1B Instruct | h$0.005 | $0.01 | — | 60K | Sep 2024 | |
Llama 3.2 3B Instruct | h$0.02 | $0.02 | — | 131K | Sep 2024 | |
Llama 3.2 11B Vision Instruct | h$0.34 | $0.34 | — | 131K | Sep 2024 | |
Meta Llama 3 8B Instruct | h$0.03 | $0.04 | — | 8K | Apr 2024 | |
Meta Llama 3 70B Instruct | h$0.30 | $0.40 | — | 8K | Apr 2024 | |
Llama 2 70B Chat Hf | h$0.64 | $0.80 | — | 4K | Jul 2023 | |
Llama 3.1 70B Instruct | h$0.40 | $0.40 | — | 131K | — | |
Llama 3.1 8B Instruct | h$0.02 | $0.04 | — | 131K | — | |
Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | 1M | — | |
Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | 1M | — | |
Llama 3 70B | h!$2.65 | $3.50 | — | — | — | |
Llama 3 8B | h!$0.30 | $0.60 | — | — | — | |
Llama 3.1 405B | h!$2.40 | $2.40 | — | — | — | |
Llama 3.1 70B | h!$0.72 | $0.72 | — | — | — | |
Llama 3.1 8B | h!$0.22 | $0.22 | — | — | — | |
Llama 3.2 11B | h!$0.16 | $0.16 | — | — | — | |
Llama 3.2 90B | h!$0.72 | $0.72 | — | — | — | |
Muse Spark Open 816B A42B | h$1.25 | $4.25 | $0.15 | — | — | |
LlamaGuard3 8B | h$0.055 | $0.055 | — | 131K | — | |
Llama 3.2 1B | h!$0.10 | $0.10 | — | — | — | |
Llama 3.2 3B | h!$0.15 | $0.15 | — | — | — | |
Llama 3.3 70B | h!$0.72 | $0.72 | — | — | — | |
Llama 4 Scout 17B 16E | h!$0.10 | $0.30 | — | — | — |
| Model | Type ↑ | Price | Released | Status |
|---|---|---|---|---|
Muse Image | Image | $0.01 / image | Jul 2026 |
34 more without a listed price
Llama pricing questions
How much does the Llama API cost?›
Llama API prices per 1M input / output tokens: Muse Spark Open $1.25 / $4.25, Muse Wonder $4 / $20, Muse Spark 1.3 $1.25 / $4.25, Muse Glimmer 30B $0.30 / $1.10, Llama Guard 4 12B $0.18 / $0.18. Cached input is about 95% cheaper.
What is the cheapest Llama model?›
Llama 3.2 1B Instruct at $0.005 / $0.01 per 1M tokens.
What is the most expensive Llama model?›
Muse Wonder at $4 / $20 per 1M tokens.
Is there a free Llama API?›
No free API tier is listed for current Meta models.