Llama 4 Scout llama-4-scout

meta-llama · llama

unranked — no quality signals yet

params
109B (A17B)
arch
moe
context
1280k
license
llama4 open weights gated
released
Apr 2025
downloads/30d
105.7k

# architecture

attn shared router expert … expert out ctx 1,310,720 109B pool · A17B/token

signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.

# trend

OGM score · last 112 days
OGM score over 112 days
overall rank (up is better)
Overall rank over 112 days

methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.

# benchmarks

benchmarkscoresourcedate
Chartqa 0.9 / 1 LLM Stats —

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime✓
Nscale 890k $0.09$0.29— via hfrouter 70 —
Amazon Bedrock — $0.09$0.33— bedrock — — ✓
DeepInfrafp8 320k $0.10$0.30— deepinfra — 66.7% ✓
DeepInfrafp8 320k $0.10$0.30— deepinfra — 100.0% ✓
DeepInfrafp8 320k $0.10$0.30— deepinfra — 84.4% ✓
Novita 128k $0.18$0.59— novita 45 — ✓
Together 1024k $0.18$0.59— via litellm — —
Googleunknown 1280k $0.25$0.70— via openrouter — —

sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price

source aliases
aa
llama-4-scout
arena
Llama-4-Scout-17B-16E-Instruct
bedrock
Llama 4 Scout 17B
openrouter
meta-llama/llama-4-scout