---
title: "Llama 4 Scout — LLM-TEST.com"
url: /models/llama-4-scout/
canonical_url: https://llm-test.com/models/llama-4-scout/
language: en
type: model
summary: "A smaller open-weight MoE sibling built around an enormous context window, aimed at whole-codebase and whole-corpus workloads on a single node."
last_updated: "2026-11-05"
---

# Llama 4 Scout

_Meta · Balanced · open weights_

A smaller open-weight MoE sibling built around an enormous context window, aimed at whole-codebase and whole-corpus workloads on a single node.

## At a glance

- Released: Feb 10, 2026
- Provider: Meta
- Context window: 10,000,000 tokens
- Max output: 16,000 tokens
- Modalities: Text + image → text
- Knowledge cutoff: August 2025
- API model ID: `llama-4-scout`
- License: Open weights (Llama 4 Community License)

## Pricing

- Standard: $0.10 input / $0.40 output per 1M tokens (aggregator estimate)
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0004 (standard)

## What's new vs Llama 3.2 11B (September 2024)

- Ten-million-token context unlocks whole-repository reasoning
- Efficient MoE routing keeps it affordable to run
- Lower peak quality than Maverick on the hardest tasks

## Best use cases

- **Whole-codebase analysis** — Loads entire repositories into context for review and refactoring.
- **Long-document synthesis** — Reasons across books, filings, or massive log dumps in one pass.
- **Edge-of-datacenter serving** — Fits on a single node while still offering huge context.

## Strengths

- Massive context
- Cheap
- Open weights

## Limitations

- Quality dips as context fills
- Below the flagship on hard reasoning

## Where to get access

- Consumer app: Meta AI (meta.ai, WhatsApp, Instagram, Messenger) — https://www.meta.ai
- API: llama.com (download the weights) — https://llama.com
- Also available: hosted by Together, Fireworks, Groq, AWS Bedrock and others
- Docs: https://llama.meta.com/docs

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/