Llama 4 Scout
Fast, affordable Llama 4 with 10M context window and image understanding.
- Input
- $0.11 / 1M tokens
- Output
- $0.34 / 1M tokens
- Cached read
- — / 1M tokens
- Cached write
- — / 1M tokens
- Batch discount
- —%
- Source
- Llama 4 Scout pricing
- Verified
- Apr 5, 2026 (High)
Capabilities
- Modalities
- textimage→text
- Capabilities
- imageInputbatchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- 10M token context, Very cheap, Open weights
- Tradeoffs
- MoE architecture, 109B total params but 17B active
Official Links
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|---|---|---|---|---|
| MMLU | 2024 | 79.6 % | Apr 1, 2025 | Meta | Vendor-reported |
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| Llama 4 Scout | llama-4-scout | Active | Apr 5, 2025 | — | — | Current published model family snapshot. |
Host Coverage
| Host | Type | Context | Pricing Note | Differences |
|---|---|---|---|---|
| Groq | cloud | 131.1K | $0.11/$0.34 per MTok. | Fast inference |
| AWS Bedrock | cloud | 10.0M | $0.17/$0.60 per MTok. | Enterprise integration |
Migration Guidance
Primary open-weight fast tier in Llama 4 family.
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Apr 5, 2025 | family_added | Llama 4 Scout published | Initial public model family launch. | Llama 4 Scout release notes |
Other models from Meta AI
Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, Llama 3.2 11B Vision, Llama 3.2 90B Vision, Llama 3.3 70B, Llama 4 Maverick