Llama 4 Scout
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-scoutLicense
Open weights (Llama 4 Community License)
Pricing
Standard
Input$0.10 / 1M
Output$0.40 / 1M
* Rates are from a third-party aggregator — verify before relying on them. A typical 1,500-token prompt with a 650-token answer costs ≈ $0.0004 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withLlama 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 & limitations
Strengths
- Massive context
- Cheap
- Open weights
Limitations
- Quality dips as context fills
- Below the flagship on hard reasoning
How to test it
- No-code: open meta.ai and pick Llama 4 Scout from the model switcher — no API key needed.
- Playground: sign in to llama.com (download the weights) and run prompts in the workbench, then copy the generated code.
- API: pick an inference host (Together, Fireworks, Groq, AWS Bedrock…), create a key and call its OpenAI-compatible endpoint, or read the docs.
# via an OpenAI-compatible inference host (Together, Fireworks, Groq, …)
curl https://<your-host>/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "llama-4-scout", "messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]}'Where to get access
Direct API
Pay-as-you-go access via llama.com (download the weights).
llama.com (download the weights) ↗