Pass IndexThe State of AISign in

Meta-Llama-3.1-405B-Instruct

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes.

text → text · made by Meta

$0.12$0.3per Mtok in / out
Hyperbolic · 9 sellers

Sold by 9 ways

SellerLaneRate
Databricks cloudstandard$5per Mtok in$15per Mtok out$5per Mtok cached$5per Mtok cache writeraw.githubusercontent.com · read 2026-09-16
AWS Bedrock cloudstandard$5.32per Mtok in$16per Mtok outraw.githubusercontent.com · read 2026-09-16
Microsoft Azure AI cloudstandard$5.33per Mtok in$16per Mtok outraw.githubusercontent.com · read 2026-09-16
Oracle Cloud Infrastructure cloudstandard$10.68per Mtok in$10.68per Mtok outraw.githubusercontent.com · read 2026-09-16
Hyperbolic aggregatorstandard$0.12per Mtok in$0.3per Mtok outraw.githubusercontent.com · read 2026-09-16
DeepInfra aggregatorstandard$0.8per Mtok in$0.8per Mtok outapi.deepinfra.com · read 2026-08-25
Requesty aggregatordeepinfra$0.8per Mtok in$0.8per Mtok out$0.8per Mtok cachedrouter.requesty.ai · read 2026-08-28
Together AI aggregatorstandard$3.5per Mtok in$3.5per Mtok outraw.githubusercontent.com · read 2026-09-16
SambaNova Cloud aggregatorstandard$5per Mtok in$10per Mtok outraw.githubusercontent.com · read 2026-09-16

Measured 12 standings

PlaceBoardMetricScore
10thof 16The agent company — Epoch AI% Score0.141
14thof 217Mmlu — Epoch AIEM0.845
15thof 137Wino grande — Epoch AIAccuracy82.2
20thof 22Cybench — Epoch AIUnguided % Solved0.075
33rdof 81Forecastbench — Epoch AIOverall score59.9
64thof 108Math level 5 — Epoch AImean_score49.773
91stof 102Simplebench — Epoch AIScore (AVG@5)0.23
112thof 161Dtbench — Epoch AIAccuracy61.38
155thof 170Weirdml — Epoch AIAccuracy21.38
227thof 313GPQA Diamondmean_score50.915
238thof 290OTIS Mock AIME 2024-2025mean_score9.722
536thof 656Epoch capabilities index — Epoch AIECI Score128.75

About

Meta-Llama-3.1-405B-Instruct — a text model from Meta, sold by 9 companies from $0.12 in and $0.3 out per million tokens, placed 14th of 217 on Mmlu — Epoch AI.

It takes text and returns text, with a context window of 32,768 tokens. It was published in July 2024, trained on material up to December 2023. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and agents. Nine companies sell it. The cheapest is $0.12 in and $0.3 out per million tokens at Hyperbolic. Beside the standard rate there is a separately routed lane. It has been measured on 12 boards, and stands best at 14th of 217 on Mmlu — Epoch AI.

Every current figure

Maker
Meta
Register
model
Takes
text
Returns
text
Context
32,768 tokens
Published
July 2024
Knowledge to
December 2023
Parameters
405 billion · read from its own name
Licence
not read
Sellers
9
Maker's own price
not read
Price
$0.12 in and $0.3 out per million tokens — Hyperbolic
Boards
12
Best place
14th of 217 — Mmlu — Epoch AI

Known as 3 names

llama3-1-405b-instructmeta-llama/Meta-Llama-3.1-405B-Instructdeepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct