Llama 4 Scout — Meta | Modeldex

Llama 4 Scout

Active

Efficient multimodal model with 17B active parameters.

Updated 3 days agoStructured data from Modeldex catalog

VisionAgenticOpen source

Knowledge cutoff

Aug 31, 2024(1.6 years ago)

API release

Apr 5, 2025(1.0 years ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

History

Llama 4 Scout became available via the Meta API on 2025-04-05.

Training & availability

Training data has a knowledge cutoff of 2024-08-31 — information about events after that date is unlikely to appear in the model's responses. Weights are publicly available, making this an open-weight model suitable for on-prem deployment and fine-tuning.

Capabilities

Input modalities: text, image.

Recommended for: vision, agentic, open-source.

Limitations

The knowledge cutoff is 19 months old — this model will not know about recent events, releases, or API changes.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="meta/llama-4-scout",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.11/1M

Output tokens / month2.0M

@ $0.34/1M

Input cost

$0.55

5.0M × $0.11/1M

Output cost

$0.68

2.0M × $0.34/1M

Total / month

$1.23

$14.76 / year

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

368.6K/ month

HuggingFace likes

1.3K

Integrations & tooling support

Tool calling: Supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.