Llama 4 Scout Instruct: pricing, context window and benchmarks
Llama 4 Scout Instruct is a multimodal model from Meta AI. It offers a 32,768-token context window, costs $4.59 per million input tokens and $20.15 per million output tokens, and averages 79.1 across the index's benchmark suite.
Pricing
Llama 4 Scout Instruct costs $4.59 per million input tokens and $20.15 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.48 per million tokens. Cached input is listed at $0.59 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.59 | per 1M tokens |
| Output | $20.15 | per 1M tokens |
| Cached input | $0.59 | per 1M tokens |
| Blended 3:1 | $8.48 | estimate per 1M tokens |
| 1M in + 1M out | $24.74 | 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 | 80.0 | 183 | 70th | |
| GPQA Diamond | 76.1 | 121 | 80th | |
| SWE-bench Verified | 70.1 | 108 | 82th | |
| HumanEval | 81.6 | 194 | 68th | |
| MATH-500 | 84.7 | 114 | 81th | |
| AIME 2025 | 77.3 | 125 | 79th | |
| LiveCodeBench | 73.8 | 113 | 81th | |
| IFEval | 85.2 | 185 | 69th | |
| TruthfulQA | 79.9 | 181 | 70th | |
| HellaSwag | 88.4 | 127 | 79th | |
| MMMU | 73.0 | 221 | 63th | |
| Arena Elo | 1429.1 | 122 | 80th |
What Llama 4 Scout Instruct is good for
Llama 4 Scout Instruct 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 $4.59 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.
Strengths
- 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 Base | Meta AI | 128000 | $4.68 | 79.1 |
| Llama 4 Scout Instruct | Meta AI | 32768 | $4.59 | 79.1 |
| Mistral Large 3 Chat | Mistral AI | 1000000 | $4.90 | 79.1 |
| Qwen3 Chat | Alibaba Cloud | 128000 | $4.75 | 79.1 |
| Sonar Pro | Perplexity | 128000 | $13.01 | 79.1 |
| Claude Opus 4.5 Mini | Anthropic | 65536 | $12.72 | 79.0 |
FAQ
How much does Llama 4 Scout Instruct cost?
Llama 4 Scout Instruct is listed at $4.59 per million input tokens and $20.15 per million output tokens. Cached input is $0.59 per million tokens. A blended 3:1 input-to-output mix is about $8.48 per million tokens.
What is the context window of Llama 4 Scout Instruct?
Llama 4 Scout Instruct has a context window of 32,768 tokens and can emit up to 4,096 output tokens per request in this index.
Is Llama 4 Scout Instruct open weights?
Yes. Llama 4 Scout Instruct is listed as an open-weight model under a open weights licence.
How does Llama 4 Scout Instruct score on benchmarks?
Llama 4 Scout Instruct averages 79.1 across the scored benchmarks in this index, ranking #145 of 600 models. Its strongest relative result is Arena Elo at 1429.1.
What is Llama 4 Scout Instruct best for?
Llama 4 Scout Instruct 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 $4.59 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.