Llama 4 Scout 1.5B: pricing, context window and benchmarks
Llama 4 Scout 1.5B is a small open-weight model from Meta AI. It offers a 8,192-token context window, costs $0.66 per million input tokens and $2.71 per million output tokens, and averages 53.0 across the index's benchmark suite.
Pricing
Llama 4 Scout 1.5B costs $0.66 per million input tokens and $2.71 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.17 per million tokens. Cached input is listed at $0.07 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.66 | per 1M tokens |
| Output | $2.71 | per 1M tokens |
| Cached input | $0.07 | per 1M tokens |
| Blended 3:1 | $1.17 | estimate per 1M tokens |
| 1M in + 1M out | $3.37 | 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 | 58.9 | 539 | 10th | |
| GPQA Diamond | 50.2 | 521 | 13th | |
| SWE-bench Verified | 38.3 | 536 | 11th | |
| HumanEval | 55.6 | 538 | 10th | |
| MATH-500 | 54.9 | 521 | 13th | |
| AIME 2025 | 43.5 | 517 | 14th | |
| LiveCodeBench | 37.7 | 552 | 8th | |
| IFEval | 64.4 | 538 | 10th | |
| TruthfulQA | 59.1 | 539 | 10th | |
| HellaSwag | 71.1 | 519 | 14th | |
| MMMU | 49.8 | 555 | 8th | |
| Arena Elo | 1222.2 | 533 | 11th |
What Llama 4 Scout 1.5B is good for
Llama 4 Scout 1.5B 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 $0.66 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.66 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Context window of 8,192 tokens is small for long-document work.
- 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 1.5B | Zhipu AI | 16384 | $0.65 | 53.3 |
| Kimi K1.5 1.5B | Moonshot AI | 4096 | $0.75 | 53.2 |
| Mixtral Turbo 7B | Together AI | 8192 | $0.68 | 53.2 |
| Llama 4 Scout 1.5B | Meta AI | 8192 | $0.66 | 53.0 |
| Qwen3-Coder 1.5B | Alibaba Cloud | 32768 | $0.76 | 52.8 |
| Magistral 1.5B | Mistral AI | 4096 | $0.67 | 52.7 |
FAQ
How much does Llama 4 Scout 1.5B cost?
Llama 4 Scout 1.5B is listed at $0.66 per million input tokens and $2.71 per million output tokens. Cached input is $0.065 per million tokens. A blended 3:1 input-to-output mix is about $1.17 per million tokens.
What is the context window of Llama 4 Scout 1.5B?
Llama 4 Scout 1.5B has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Llama 4 Scout 1.5B open weights?
Yes. Llama 4 Scout 1.5B is listed as an open-weight model under a open weights licence.
How does Llama 4 Scout 1.5B score on benchmarks?
Llama 4 Scout 1.5B averages 53.0 across the scored benchmarks in this index, ranking #536 of 600 models. Its strongest relative result is Arena Elo at 1222.2.
What is Llama 4 Scout 1.5B best for?
Llama 4 Scout 1.5B 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 $0.66 per million input tokens it can handle a large share of production traffic.