Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model de...
About
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high effic
Details
| Modality | image, text |
| Context Window | 327.7K tokens |
| Release Date | Apr 5, 2025 |
| API Available | Yes |
| Hosting | self-hosted, api |
| Output Speed | 250 tokens/sec |
| Time to First Token | 250ms |
| Quality Index | 68/100 |
| Coding Index | 62/100 |
| Reasoning Index | 66/100 |
Benchmarks
Resources
Tags
Quick Info
- Organization
- Meta
- Pricing
- Free (self-hosted) / $0.08/1M input tokens (API)
- Free Tier
- Yes
- Popularity
- 44/100
- Updated
- Feb 20, 2026
Also in AI Models
Claude Opus 4.6
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional...
Claude Sonnet 4.6
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier per...
Gemini 3 Flash
Google DeepMind's latest fast and capable multimodal AI model