Llama 4 Maverick: pricing, context window and benchmarks
Llama 4 Maverick is a multimodal model from Meta AI. It offers a 200,000-token context window, costs $5.36 per million input tokens and $25.19 per million output tokens, and averages 81.6 across the index's benchmark suite.
Pricing
Llama 4 Maverick costs $5.36 per million input tokens and $25.19 per million output tokens. A blended 3:1 input-to-output mix works out to about $10.32 per million tokens. Cached input is listed at $0.69 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.36 | per 1M tokens |
| Output | $25.19 | per 1M tokens |
| Cached input | $0.69 | per 1M tokens |
| Blended 3:1 | $10.32 | estimate per 1M tokens |
| 1M in + 1M out | $30.55 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 84.7 | 67 | 89th | |
| GPQA Diamond | 76.8 | 107 | 82th | |
| SWE-bench Verified | 71.8 | 77 | 87th | |
| HumanEval | 87.3 | 83 | 86th | |
| MATH-500 | 82.7 | 151 | 75th | |
| AIME 2025 | 79.6 | 94 | 84th | |
| LiveCodeBench | 75.7 | 87 | 86th | |
| IFEval | 87.5 | 117 | 81th | |
| TruthfulQA | 82.6 | 115 | 81th | |
| HellaSwag | 88.2 | 134 | 78th | |
| MMMU | 80.4 | 54 | 91th | |
| Arena Elo | 1447.0 | 84 | 86th |
What Llama 4 Maverick is good for
Llama 4 Maverick is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $5.36 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 4 Maverick Instruct | Meta AI | 200000 | $5.33 | 81.7 |
| Mistral Large 3 | Mistral AI | 128000 | $5.41 | 81.7 |
| Claude 3.7 Sonnet | Anthropic | 200000 | $14.91 | 81.6 |
| Doubao 1.5 Pro Reasoning | ByteDance | 128000 | $14.56 | 81.6 |
| Gemini 2.5 Pro | Google DeepMind | 200000 | $15.20 | 81.6 |
| Llama 4 Maverick | Meta AI | 200000 | $5.36 | 81.6 |
FAQ
How much does Llama 4 Maverick cost?
Llama 4 Maverick is listed at $5.36 per million input tokens and $25.19 per million output tokens. Cached input is $0.69 per million tokens. A blended 3:1 input-to-output mix is about $10.32 per million tokens.
What is the context window of Llama 4 Maverick?
Llama 4 Maverick has a context window of 200,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is Llama 4 Maverick open weights?
Yes. Llama 4 Maverick is listed as an open-weight model under a open weights licence.
How does Llama 4 Maverick score on benchmarks?
Llama 4 Maverick averages 81.6 across the scored benchmarks in this index, ranking #94 of 600 models. Its strongest relative result is Arena Elo at 1447.0.
What is Llama 4 Maverick best for?
Llama 4 Maverick is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $5.36 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.