llama-4-scout

1322 Score third-party Elo · arena.ai / LMArena ?

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...

LLM & Generative AI 1 model 1 listings snapshot Oct 14, 2026, 12:43 AM

Platforms

click a card to open the detail table

Cheapest OpenRouter no official benchmark Input$0.180 Output$0.590 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
meta-llama/llama-4-scout	OpenRouter	1M contextmultimodal	$0.180	$0.590

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

dataviz 896 · 39.3% wr
codecategories 792 · 26.6% wr
gamedev 777 · 27.4% wr
uicomponent 769 · 25.5% wr
website 753 · 22.7% wr

Input / Output modalities modality: text+image->text

text in+out
image input only

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
DeepInfra	meta-llama/Llama-4-Scout-17B-16E-Instruct	$0.100	$0.300	—	—	—	2026-10-14 00:43:44
Novita	meta-llama/llama-4-scout-17b-16e-instruct	$0.180	$0.590	—	—	—	2026-10-14 00:54:15
OpenRouter	meta-llama/llama-4-scout	$0.180	$0.590	128.1 ms	—	100% available	2026-10-14 00:43:21
Together	meta-llama/Llama-4-Scout-17B-16E-Instruct	$0.180	$0.590	—	—	—	2026-10-14 00:53:13

4 rows · snapshot 2026-10-14 00:43:21 · from data/public/prices.json + measurements.json