Llama 4 Scout 7B: pricing, context window and benchmarks
Llama 4 Scout 7B is a small open-weight model from Meta AI. It offers a 32,768-token context window, costs $1.30 per million input tokens and $5.58 per million output tokens, and averages 60.0 across the index's benchmark suite.
Pricing
Llama 4 Scout 7B costs $1.30 per million input tokens and $5.58 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.37 per million tokens. Cached input is listed at $0.14 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.30 | per 1M tokens |
| Output | $5.58 | per 1M tokens |
| Cached input | $0.14 | per 1M tokens |
| Blended 3:1 | $2.37 | estimate per 1M tokens |
| 1M in + 1M out | $6.88 | 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 | 63.3 | 484 | 19th | |
| GPQA Diamond | 53.9 | 483 | 20th | |
| SWE-bench Verified | 45.9 | 454 | 24th | |
| HumanEval | 61.2 | 483 | 20th | |
| MATH-500 | 61.4 | 449 | 25th | |
| AIME 2025 | 53.1 | 433 | 28th | |
| LiveCodeBench | 51.3 | 435 | 28th | |
| IFEval | 70.5 | 449 | 25th | |
| TruthfulQA | 64.9 | 460 | 23th | |
| HellaSwag | 74.6 | 447 | 26th | |
| MMMU | 60.0 | 429 | 29th | |
| Arena Elo | 1265.6 | 468 | 22th |
What Llama 4 Scout 7B is good for
Llama 4 Scout 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $1.30 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.30 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GLM-4.5 7B | Zhipu AI | 8192 | $1.32 | 60.2 |
| GPT-NeoX Chat | EleutherAI | 16384 | $1.49 | 60.1 |
| Llama 3.3 8B | Meta AI | 8192 | $1.26 | 60.1 |
| Llama 4 Scout 7B | Meta AI | 32768 | $1.30 | 60.0 |
| Magistral 8B | Mistral AI | 4096 | $1.33 | 60.0 |
| Kimi K1.5 7B | Moonshot AI | 8192 | $1.35 | 59.9 |
FAQ
How much does Llama 4 Scout 7B cost?
Llama 4 Scout 7B is listed at $1.30 per million input tokens and $5.58 per million output tokens. Cached input is $0.14 per million tokens. A blended 3:1 input-to-output mix is about $2.37 per million tokens.
What is the context window of Llama 4 Scout 7B?
Llama 4 Scout 7B has a context window of 32,768 tokens and can emit up to 16,384 output tokens per request in this index.
Is Llama 4 Scout 7B open weights?
Yes. Llama 4 Scout 7B is listed as an open-weight model under a open weights licence.
How does Llama 4 Scout 7B score on benchmarks?
Llama 4 Scout 7B averages 60.0 across the scored benchmarks in this index, ranking #451 of 600 models. Its strongest relative result is Arena Elo at 1265.6.
What is Llama 4 Scout 7B best for?
Llama 4 Scout 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $1.30 per million input tokens it can handle a large share of production traffic.