Meta: Llama 4 Scout
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...
Specification
- Model ID
- meta-llama/llama-4-scout
- Weight license
- Not verified; consult the exact publisher model card
- Modality
- Text+image >text
- Context
- 327.7K tokens
- Input
- $0.100/1M
- Output
- $0.300/1M
- Updated
- Nov 14, 2026
Scores
Capabilities
- Supports tool calling
- Supports vision inputs
- Supports long-context workflows
- Lighter reasoning profile
Input and output
Accepts Text, Image inputs. Returns Text outputs.
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Related models
Build with Meta: Llama 4 Scout
Describe what you want to make and pick this model in the composer. A database and hosting are included.