Meta/ Llama
Llama 4 Scout
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...
Released
2025-04-05
Context window
1.3M
Max output
16K
Weights
Open weight
Modalities
Input
TextImage
Output
Text
Identity
- Version
- llama-4-scout
- Knowledge cutoff
- 2024-08-31
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | meta-llama/llama-4-scout | openai_chat | 1.3M | 16K | TextImage | Text | Tool callStructuredTemperatureOpen weight | Hugging Face: meta-llama/Llama-4-Scout-17B-16E-Instruct | input $0.1/M output $0.3/M | Yes |
| NanoGPT | meta-llama/llama-4-scout | openai_chat | 1.3M | 16K | TextImage | Text | Tool callStructuredTemperatureOpen weight | - | input $0.085/M · cache read $0.0425/M output $0.46/M | Yes |
| Kilo Gateway | meta-llama/llama-4-scout | openai_chat | 1.3M | 16K | TextImage | Text | Tool callStructuredTemperatureOpen weight | - | input $0.1/M output $0.3/M | Yes |
Capabilities
Tool callStructuredTemperatureOpen weight