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.

ChatMeta1M tokens$0.109 / $0.327 · 1M

meta-llama/llama-4-scout

Context
1M tokens
Completion cap
16,384
Tools
Yes
JSON
Yes
Released
2025-04-05

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-scout",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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. Llama 4 Scout runs on the Geek Hub API (OpenAI-compatible). Model id: meta-llama/llama-4-scout.
Is Llama 4 Scout free?
No. Input is $0.109 per 1M tokens and output is $0.327 per 1M tokens on Geek Hub (markup included).
What is the context length of Llama 4 Scout?
Llama 4 Scout has a 1M tokens context window. It supports up to 16,384 completion tokens.
Does Llama 4 Scout support tool calling and structured outputs?
Llama 4 Scout accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Llama 4 Scout released?
Llama 4 Scout was released on 2025-04-05.

More models from Meta