Llama 3.1 405B Instruct llama-3.1-405b-instruct

meta-llama · llama flagship

unranked — no quality signals yet

params
405B
arch
dense
license
llama3.1 open weights gated
released
Jul 2024
downloads/30d
9.4k

# architecture

attn shared feed-forward (dense) every parameter, every token out 405B — no routing

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 106 days
OGM score over 106 days

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

# benchmarks

benchmarkscoresourcedate
Api-bank 0.9 / 1 LLM Stats —
Arc-c 1.0 / 1 LLM Stats —
Bfcl 0.9 / 1 LLM Stats —
Gsm8k 1.0 / 1 LLM Stats —

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime✓
Hyperbolic 32k $0.12$0.30— via litellm — —
DeepInfra 130k $0.80$0.80$0.80 via requesty — —
Nebius 125k $1.00$3.00— via litellm — —
Together 4k $3.50$3.50— via litellm — —

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-3-1-405b-instruct
arena
Llama-3.1-405B-Instruct
hf
meta-llama/Meta-Llama-3.1-405B-Instruct
openrouter
meta-llama/llama-3.1-405b-instruct