Meta: Llama 4 Scout
meta-llama/llama-4-scout
153rd smartest of 182Cheaper than 83% of paidToolsJSONVision
Intelligence
10.0
153rd of 182
Design Elo
925
Data Viz
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.100
57th cheapest
Context
1.3M
16K max out
How it compares
Smarter than16%
of all ranked models
Cheaper than83%
of all ranked models
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis36th percentile
Intelligence Index
10.0
Coding Index
8.2
GPQA Diamond
59%
Humanity's Last Exam
4%
SciCode
17%
Tau²-Bench (agentic)
15%
Design Arena · Elo56 tournaments
Data Viz
925
Website
774
Providers & pricing (4)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.100 | $0.300 | 328K | 100% |
| Groq | $0.110 | $0.340 | 131K | 97.7% |
| Novitabf16 | $0.180 | $0.590 | 131K | 100% |
| $0.250 | $0.700 | 1.3M | 99.4% |
Specifications
Context window1.3M
Max output16K
Knowledge cutoffAug 2024
Input modalitiestext, image
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsmeta-llama/Llama-4-Scout-17B-16E-Instruct ↗
Llama 4 Scout FAQ
How much does Llama 4 Scout cost?
Llama 4 Scout costs $0.100 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 57th cheapest of 332 paid models.
How smart is Llama 4 Scout?
Llama 4 Scout scores 10.0 on the Artificial Analysis Intelligence Index, ranking 153rd of 182 benchmarked models, with a GPQA Diamond score of 59%.
What is Llama 4 Scout's context window?
Llama 4 Scout supports a 1.3M-token context window and can output up to 16K tokens. It accepts text, image input.