Plain-English Summary
A more deployable Llama 4 model notable for its extremely long context window.
Llama 4 Scout
A more deployable Llama 4 model notable for its extremely long context window.
Llama 4
Multimodal LLM
Open weights
Open weights: Yes
API: Via Meta and partners
Technical Notes
Native multimodal MoE model with 17B active parameters, 16 experts, about 109B total parameters, and up to 10M context.
Best For
Very long documents, large codebases, multimodal RAG, self-hosting
Watch Out For
The full 10M context may require specialized infrastructure and quality can vary across the window.
Model Specs
- Maker
- Meta
- Country
- USA
- Family
- Llama 4
- Type
- Multimodal LLM
- Release date
- 2025-04-05
- Date confidence
- Exact
- Status
- Open weights
- Context window
- 10,000,000 tokens
- Max output
- Not listed
- Parameters
- ~109B
- Active parameters
- 17B
- Architecture
- Mixture-of-experts multimodal transformer
- Reasoning
- Yes
- Tool calling
- Host dependent
- Structured output
- Host dependent
- API available
- Via Meta and partners
- Open weights
- Yes
- Self-hostable
- Yes
- License
- Llama 4 Community License
- Inputs
- Text, image
- Outputs
- Text
- Approx. price
- See provider pricing
- How to access
- Provider website
- Model / API ID
- Llama-4-Scout
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Fine-tuning, quantization, self-hosting
- Completeness
- 95 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source