Llama 4 Scout: pricing, context window and benchmarks
Llama 4 Scout is a multimodal model from Meta AI. It offers a 200,000-token context window, costs $4.90 per million input tokens and $24.91 per million output tokens, and averages 79.3 across the index's benchmark suite.
Pricing
Llama 4 Scout costs $4.90 per million input tokens and $24.91 per million output tokens. A blended 3:1 input-to-output mix works out to about $9.90 per million tokens. Cached input is listed at $0.44 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.90 | per 1M tokens |
| Output | $24.91 | per 1M tokens |
| Cached input | $0.44 | per 1M tokens |
| Blended 3:1 | $9.90 | estimate per 1M tokens |
| 1M in + 1M out | $29.81 | 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 | 81.9 | 123 | 80th | |
| GPQA Diamond | 74.1 | 165 | 73th | |
| SWE-bench Verified | 70.4 | 103 | 83th | |
| HumanEval | 86.5 | 96 | 84th | |
| MATH-500 | 81.0 | 192 | 68th | |
| AIME 2025 | 74.2 | 173 | 71th | |
| LiveCodeBench | 72.1 | 145 | 76th | |
| IFEval | 86.9 | 136 | 77th | |
| TruthfulQA | 82.1 | 128 | 79th | |
| HellaSwag | 88.9 | 114 | 81th | |
| MMMU | 74.1 | 188 | 69th | |
| Arena Elo | 1431.8 | 119 | 80th |
What Llama 4 Scout is good for
Llama 4 Scout 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 $4.90 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 |
|---|---|---|---|---|
| Claude Haiku 4.5 | Anthropic | 1000000 | $13.86 | 79.4 |
| Nova Pro | Amazon | 32768 | $12.75 | 79.4 |
| Llama 4 Scout | Meta AI | 200000 | $4.90 | 79.3 |
| Reka Core Max | Reka AI | 128000 | $13.41 | 79.3 |
| Claude Haiku 4.5 Vision | Anthropic | 128000 | $13.01 | 79.2 |
| Kimi K2 Base | Moonshot AI | 65536 | $4.82 | 79.2 |
FAQ
How much does Llama 4 Scout cost?
Llama 4 Scout is listed at $4.90 per million input tokens and $24.91 per million output tokens. Cached input is $0.44 per million tokens. A blended 3:1 input-to-output mix is about $9.90 per million tokens.
What is the context window of Llama 4 Scout?
Llama 4 Scout has a context window of 200,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Llama 4 Scout open weights?
Yes. Llama 4 Scout is listed as an open-weight model under a open weights licence.
How does Llama 4 Scout score on benchmarks?
Llama 4 Scout averages 79.3 across the scored benchmarks in this index, ranking #140 of 600 models. Its strongest relative result is Arena Elo at 1431.8.
What is Llama 4 Scout best for?
Llama 4 Scout 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 $4.90 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.