Home › Models › Llama 4 Scout
Llama 4 Scout API pricing
Llama 4 Scout is a model from Meta (Llama) with a 10,000,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026.
Price list
| Token class | Rate / 1M | Notes |
|---|---|---|
| Input | $0.18 | Prompt tokens not served from cache |
| Cached input | $0.018 | 90% below base input |
| Cache write |  | Not billed per token |
| Output | $0.59 | 3.3× the input rate |
| Batch API | −50% | Input and output, results within 24 h |
Open weights. 17B active params, 10M context window. Priced via Together AI.
What Llama 4 Scout costs at three real workloads
Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.
| Workload | Requests | Tokens | Estimated cost |
|---|---|---|---|
| Support chat | 1,000 | 4K in / 600 out | $1.07 |
| RAG with caching | 1,000 | 50K in (45K cached) / 1K out | $2.31 |
| Nightly batch job | 10,000 | 10K in / 2K out | $14.90 |
Caching the 45K-token prefix saves about 76% on the RAG workload versus sending it uncached every call ($9.59 → $2.31). Batch mode halves the nightly job.
Where Llama 4 Scout sits in the market
Out of 37 models in this dataset, Llama 4 Scout ranks #6 cheapest by input rate, #5 by output rate, and #6 on a blended 1M-input-plus-250K-output workload.
| Model | Provider | Input | Output | Blended |
|---|---|---|---|---|
| Llama 4 Scout | Meta (Llama) | $0.18 | $0.59 | $0.328 |
| Qwen 3 32B | Alibaba (Qwen) | $0.15 | $0.60 | $0.30 |
| Llama 4 Maverick | Meta (Llama) | $0.27 | $0.85 | $0.483 |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | $0.225 |
Blended cost = 1M input tokens + 250K output tokens at list price.
FAQ
How much does Llama 4 Scout cost per 1M tokens?
$0.18 per 1M input tokens and $0.59 per 1M output tokens on the standard tier.
Is prompt caching cheaper on Llama 4 Scout?
Yes. Cached input bills at $0.018 per 1M tokens, 90.0% below the $0.18 base input rate, with no separate cache-write rate published.
Does Llama 4 Scout support the Batch API?
Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $29.80 at list price and about $14.90 in batch mode.
Keep reading
- All Meta (Llama) models and rates
- Every model in the dataset, ranked by price
- Llama 4 Maverick vs Llama 4 Scout
- GPT-6 Luna vs Llama 4 Scout
- Claude Haiku 4.5 vs Llama 4 Scout
- Calculate your own monthly cost with the free estimator
Run these numbers in the calculator