Meta: Llama 4 Scout
Provider: meta-llama · meta-llama/llama-4-scout
How Meta: Llama 4 Scout pricing compares
At $0.34 / 1M output tokens, Meta: Llama 4 Scout is the 5th-cheapest of 8 meta-llama models we track. It's cheaper than 84% of the 392 paid models on computetrail (62nd-cheapest overall). Output costs 3.1× its input price ($0.11 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.17 / 1M blended. Reading cached input costs 50% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 1,310,720 tokens context window ranks 6th-largest of 392 models with a published limit.
Output price history
Across 60 daily snapshots since 2026-06-29, the output price has risen 13.3% — from $0.3 to $0.34 / 1M.
Similar-priced models
| Model | Provider | Output $/1M | Context |
|---|---|---|---|
| Meta: Llama 3.2 3B Instruct | meta-llama | $0.33 | 131,072 |
| DeepSeek: DeepSeek V3.2 | deepseek | $0.38 | 163,840 |
| NVIDIA: Nemotron 3 Super | nvidia | $0.4 | 1,000,000 |
| Qwen: Qwen3 32B | qwen | $0.28 | 131,072 |
| Meta: Llama 3.1 70B Instruct | meta-llama | $0.4 | 131,072 |
| DeepSeek: DeepSeek V3.2 Exp | deepseek | $0.41 | 163,840 |
Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.