Llama 4 Scout
Provider: Meta Llama US
Overview
Meta developed Llama 4 Scout as a 109B parameter mixture-of-experts model with 17B active parameters, targeting large-context multimodal workloads.
Strengths
- 1,310,720 token context window
- Native vision, function-calling, and JSON mode support
- 16,384 maximum output tokens
- Knowledge cutoff of August 2024
Best use cases
- Processing large multi-megabyte document repositories
- Multimodal analysis requiring vision input
- Structured data extraction via JSON mode
Pricing position
Priced at $0.1/M input and $0.3/M output, matching Voxtral Small and Mistral Small 3.2 while offering half the output cost of GPT-4.1 Nano.
Caveats
Max output is capped at 16,384 tokens despite the 1.3M input capacity. No free tier exists.
Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.
Key facts
- Price basis
- Median third-party host price (no first-party API)
- Max output
- 16K tokens
- Knowledge cutoff
- 2024-08-31
- Listed on OpenRouter
- 2025-04-05
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-10
Features
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.03 |
| 1M (small app) | 1 | 0.5 | $0.25 |
| 10M (mid scale) | 10 | 5 | $2.50 |
| 100M (large) | 100 | 50 | $25.00 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Meta Llama
Similar-priced models
Source: OpenRouter API (meta-llama/llama-4-scout)