Meta: Llama 4 Scout✓ Catalog verified
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.
Overview
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.
Access: available through the official Meta API. Context window: 328K.
Specifications
| API identifier | meta-llama/llama-4-scout |
| Provider | Meta |
| Model type | Multimodal LLM |
| Context window | 328K catalog |
| Input modalities | text · image |
| Output modalities | text |
| Released | Apr 5, 2025 |
| Tokenizer | Llama4 |
| Moderated | No |
| Architecture modality | text+image->text |
Pricing
Live pricing components for meta-llama/llama-4-scout as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $8e-8 | $0.08 / 1M | Per input token |
| Completion tokens | $3e-7 | $0.30 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.1Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | ✓ Supported | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | ✓ Supported | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Meta: Llama 4 Scout through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="meta-llama/llama-4-scout",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| Amazon: Nova Lite 1.0 | Amazon | 300K | $0.06 | View → |
| Amazon: Nova Pro 1.0 | Amazon | 300K | $0.80 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Meta: Llama 4 Scout cost?
$0.08 per 1M input tokens and $0.30 per 1M output tokens on the official Meta API.
What is the context window of Meta: Llama 4 Scout?
Meta: Llama 4 Scout supports up to 328K tokens of context.
Does Meta: Llama 4 Scout support tool / function calling?
Yes, Meta: Llama 4 Scout supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Meta: Llama 4 Scout?
Use the official Meta API with the model id `meta-llama/llama-4-scout`. See the Quick start section above for code examples.