Llama 4 Scout

meta-llama/llama-4-scout

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Llama 4 Scout

open weights tools

Meta meta-llama/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...

Input $/1M: $0.10
Output $/1M: $0.30
Context: 1.3M
Max output: 16K
Released: Apr 5, 2025
Modalities: textimage

Intelligence index7

Coding index8

Agentic index1

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Llama 4 Scout
targets:
  - id: llama-4-scout
    kind: llm
    name: Llama 4 Scout
    metadata:
      model: meta-llama/llama-4-scout          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1310720
    cost:
      usd_per_1k_tokens: 0.000200

Price among Meta models

Input list price per million tokens; Llama 4 Scout is the 4th cheapest of 8 listed.

More from Meta

Other models by the same vendor in the catalogue.