Skip to content
Free
ModelsLlamaopen weights2 providers

Llama 4 Scout 17B 16E Instruct

Open multimodal Llama model for long-context analysis and efficient agents

Best input price

$0.20

per million tokens

Context window
128,000

tokens

Reasoning
No
Tool calling
Supported
Released
2025-04-05

Inference providers2 hosting Llama 4 Scout 17B 16E Instruct

  • Azure

    llama-4-scout-17b-16e-instruct

    128,000 context$0.78 out / 1M
    $0.20

    in / 1M

    Docs

  • Azure Cognitive Services

    llama-4-scout-17b-16e-instruct

    128,000 context$0.78 out / 1M
    $0.20

    in / 1M

    Docs