Is Llama 4 Scout available on FastMetal?

Not at the moment. GLM 5.3 Flash, from the same lab, is available on the FastMetal API today.

What is the context window of Llama 4 Scout?

327,680 tokens, shared between the prompt and the response.

How does Llama 4 Scout rank?

#171 on the public arena's Japanese board (ELO 1,261). Ranks move as the leaderboard is updated.

Back to Models

meta-llama/llama-4-scout

Not Available

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 (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

4/5/2025

327,680 tokens

#109 Vision (Overall)

Specifications

Modalities

Input

text

image

Output

text

Supported Parameters

frequency_penalty

max_tokens

min_p

presence_penalty

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

16,384

Frequently asked questions

Is Llama 4 Scout available on FastMetal?: Not at the moment. GLM 5.3 Flash, from the same lab, is available on the FastMetal API today.
What is the context window of Llama 4 Scout?: 327,680 tokens, shared between the prompt and the response.
How does Llama 4 Scout rank?: #171 on the public arena's Japanese board (ELO 1,261). Ranks move as the leaderboard is updated.