Meta · open weights
Llama 4 Maverick API pricing by provider
Llama 4 Maverick is available from 5 providers. The cheapest is DigitalOcean at $0.1875 input / $0.6525 output per 1M tokens. The priciest host, Google, charges 1.8x the cheapest.
Prices from the OpenRouter API, retrieved September 15, 2026. Weights: meta-llama/Llama-4-Maverick-17B-128E-Instruct.
| Provider | Precision | Input / 1M | Output / 1M | Document Q&A / month | Context | Max output |
|---|---|---|---|---|---|---|
| DigitalOcean | — | $0.1875 | $0.6525 | $94.58 | 128K | 16K |
| DeepInfra | fp8 | $0.20 | $0.80 | $104.00 | 1.05M | 16K |
| Novita | fp8 | $0.27 | $0.85 | $133.50 | 1.05M | 8K |
| Parasail | fp8 | $0.35 | $1.00 | $170.00 | 524K | 33K |
| — | $0.35 | $1.15 | $174.50 | 524K | 8K |
Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.
Frequently asked questions
- What is the cheapest Llama 4 Maverick API provider?
- DigitalOcean is the cheapest healthy provider we track at $0.1875 per 1M input tokens and $0.6525 per 1M output tokens.
- How much does Llama 4 Maverick cost?
- Across 5 providers, input prices range from $0.1875 to $0.35 per 1M tokens and output prices from $0.6525 to $1.15.
- What is Llama 4 Maverick’s context window?
- Llama 4 Maverick supports up to 1.05M tokens, but some providers serve a smaller context window — check the table before choosing.
Other open-weight models
- DeepSeek V4.1 Flashfrom $0.15 / $0.60
- DeepSeek V4 Pro 0813from $0.96 / $2.88
- Kimi K3from $2.10 / $10.95
- GLM 5.3from $0.91 / $2.86
- GLM 5.3 Flashfrom $0.075 / $0.25
- Qwen3.8 27Bfrom $0.15 / $2.00
- MiniMax M3from $0.23 / $0.96
- gpt-oss-120bfrom $0.03 / $0.17
- gpt-oss-20bfrom $0.02 / $0.10
- Llama 3.3 70B Instructfrom $0.10 / $0.32
- Gemma 4 31Bfrom $0.09 / $0.34
- Mistral Small 4from $0.15 / $0.60
- Nemotron 3 Superfrom $0.085 / $0.40