Llama 4 Maverick API pricing
As of October 21, 2026, Meta Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens, the median of 3 providers on OpenRouter, with cached input at $0.05 per million.
Llama 4 Maverick benchmarks and specs · Every Meta Llama model's price
- Input, per million tokens$0.35
- Output, per million tokens$1.00
- Cached input, per million$0.05
- Context window524K tokens
- Max output16K tokens
- Output speed51 tok/s
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0008 | $0.850 | Yes |
| Repository review | 50K input + 3K output tokens | $0.021 | $20.50 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.080 | $80.00 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $1.491 | $1491.00 |
Price history
The price of Llama 4 Maverick here is the median across 3 providers on OpenRouter, so we do not track price changes for it.
Cheaper models as good as Llama 4 Maverick
Models within two points of Llama 4 Maverick or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Gemma 3 4B$0.075 Overall 22.6 against 21.8 · 93% cheaper output
- Phi 4$0.14 Overall 24.7 against 21.8 · 86% cheaper output
- gpt-oss-20b$0.15 Overall 38.5 against 21.8 · 85% cheaper output
- Gemma 3 12B$0.1625 Overall 28.0 against 21.8 · 84% cheaper output
- Qwen3.5-Flash$0.26 Overall 50.1 against 21.8 · 74% cheaper output
Llama 4 Maverick pricing questions
- How much does Llama 4 Maverick cost per million tokens?
- $0.35 per million input tokens and $1.00 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does Llama 4 Maverick support prompt caching?
- Yes. OpenRouter lists cached input at $0.05 per million tokens, against $0.35 for uncached input.
- Is there a cheaper model as good as Llama 4 Maverick?
- Gemma 3 4B scores 22.6 on the LLMBenchmark Index, within two points of Llama 4 Maverick or above it, and costs $0.075 per million output tokens.
- Has the price of Llama 4 Maverick changed?
- The price of Llama 4 Maverick here is the median across 3 providers on OpenRouter, so we do not track price changes for it.