Llama 4 Scout: price, context window and capabilities
Prices updated 8 Nov 2026
Llama 4 Scout is a model from Meta (meta-llama/llama-4-scout). It supports tool use. It costs $0.100 per million input tokens and $0.300 per million output tokens, with a 1.3M-token context window.
What it costs in practice
Using the listed prices: a chat turn of 2,000 input and 500 output tokens costs about $0.0003, so 10,000 such turns cost about $3.50. Summarising a 100,000-token document into 2,000 tokens costs about $0.011. A long agent run that reads 1 million tokens and writes 50,000 costs about $0.115.
Llama 4 Scout compared with its closest rivals
| Model | Input / 1M | Output / 1M | Context | Chat turn |
|---|---|---|---|---|
| Llama 4 Scout Meta | $0.100 | $0.300 | 1.3M | $0.0003 |
| Devstral 2 2512 Mistral AI | $0.400 | $2.00 | 262K | $0.0018 |
Rivals are the models from other providers with the same tool and reasoning support whose output price is closest to Llama 4 Scout's.
How it compares
Among the 40 models we track, Llama 4 Scout ranks #6 by input price and #3 by output price (1 is cheapest), and #1 by context window (1 is largest). No tracked model with the same tool and reasoning support is cheaper per output token.
More from Meta
All Meta models on one page: Meta API pricing.
- Llama 4 Maverick: $0.350 in / $1.00 out, 524K context
- Llama 3.3 70B Instruct: $0.590 in / $0.790 out, 131K context
- Llama 3.2 1B Instruct: $0.027 in / $0.201 out, 60K context
Prices and limits come from OpenRouter's public model catalogue, last synced 8 Nov 2026. Provider pricing can differ from OpenRouter's and changes often; confirm on the provider's own page before you commit. See the guide to choosing a model or the full comparison.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.