Model Information
| Slug | llama-4-scout |
|---|---|
| LLM.txt | View |
| Release Date | April 5, 2025 |
| GPQA | 0.572 |
Organization
| Name | Meta |
|---|---|
| Website | https://www.llama.com/ |
Model Description
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.
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.
Available at 17 Providers
| Provider | Type | Model Name | Original Model | Input ($/1M) | Output ($/1M) | Free | Actions | |
|---|---|---|---|---|---|---|---|---|
|
|
Helicone |
Meta Llama 4 Scout 17B 16E
|
llama-4-scout
|
$0.08 | $0.30 | |||
|
|
OpenRouter |
Chat
Code
|
Llama 4 Scout
|
meta-llama/llama-4-scout
|
$0.08 | $0.30 | ||
|
|
Kilo Code |
Code
|
Meta: Llama 4 Scout
|
meta-llama/llama-4-scout
|
$0.08 | $0.30 | ||
|
|
Blackbox AI |
Code
|
Meta: Llama 4 Scout
|
meta-llama/llama-4-scout
|
$0.08 | $0.30 | ||
|
|
WaveSpeed AI |
Chat
Code
|
llama-4-scout
|
meta-llama/llama-4-scout
|
$0.09 | $0.33 | ||
|
|
Routeway |
Meta: Llama 4 Scout
|
llama-4-scout
|
$0.10 | $0.23 | |||
|
|
Mammouth AI |
Chat
|
llama-4-scout
|
llama-4-scout
|
$0.15 | $0.60 | ||
|
|
Vercel AI Gateway |
Llama 4 Scout 17B 16E Instruct
|
llama-4-scout
|
$0.17 | $0.66 | |||
|
|
AIHubMix |
llama-4-scout
|
llama-4-scout
|
$0.20 | $0.20 | |||
|
|
CometAPI |
Llama-4-Scout
|
llama-4-scout
|
$0.22 | $1.15 | |||
|
|
Nano-GPT |
Llama 4 Scout
|
meta-llama/llama-4-scout
|
- | - | |||
|
|
ValorGPT |
Llama 4 Scout
|
meta-llama-llama-4-scout
|
- | - | |||
|
|
Yupp |
Chat
|
Llama 4 Scout (OpenRouter)
|
meta-llama/llama-4-scout
|
- | - | ||
|
|
LangDB |
llama-4-scout
|
llama-4-scout
|
- | - | |||
|
|
Okara |
Chat
|
Llama 4 Scout
|
llama-4-scout
|
- | - | ||
|
|
Airforce API |
llama-4-scout
|
llama-4-scout
|
- | - | |||
|
|
Writingmate |
Chat
Code
|
Meta: Llama 4 Scout
|
meta-llama/llama-4-scout
|
- | - |