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
Sold by 9 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | standard | $2.4per Mtok in$2.4per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Databricks 0 ways | $5per Mtok in$15per Mtok out$5per Mtok cached$5per Mtok cache write | |
| Databricks cloudnot on the seller's list today | standard | $5per Mtok in$15per Mtok out$5per Mtok cached$5per Mtok cache writeraw.githubusercontent.com · read 2026-09-22 |
| Microsoft Azure AI 0 ways | $5.33per Mtok in$16per Mtok out | |
| Microsoft Azure AI cloudnot on the seller's list today | standard | $5.33per Mtok in$16per Mtok outraw.githubusercontent.com · read 2026-09-22 |
| Oracle Cloud Infrastructure cloud | standard | $10.68per Mtok in$10.68per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Hyperbolic aggregator | standard | $0.12per Mtok in$0.3per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| DeepInfra aggregator | standard | $0.8per Mtok in$0.8per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Requesty aggregator | deepinfra | $0.8per Mtok in$0.8per Mtok out$0.8per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Together AI aggregator | standard | $3.5per Mtok in$3.5per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| SambaNova Cloud 0 ways | $5per Mtok in$10per Mtok out | |
| SambaNova Cloud aggregatornot on the seller's list today | standard | $5per Mtok in$10per Mtok outraw.githubusercontent.com · read 2026-09-22 |
Measured 12 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 10thof 16 | The agent company — Epoch AI | % Score | 0.141 |
| 14thof 217 | Mmlu — Epoch AI | EM | 0.845 |
| 15thof 137 | Wino grande — Epoch AI | Accuracy | 82.2 |
| 20thof 22 | Cybench — Epoch AI | Unguided % Solved | 0.075 |
| 58thof 92 | Forecastbench — Epoch AI | Overall score | 62.6 |
| 64thof 108 | Math level 5 — Epoch AI | mean_score | 49.773 |
| 91stof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.23 |
| 158thof 173 | Weirdml — Epoch AI | Accuracy | 21.38 |
| 186thof 235 | Dtbench — Epoch AI | Accuracy | 61.38 |
| 240thof 326 | GPQA Diamond | mean_score | 50.915 |
| 254thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 9.722 |
| 256thof 260 | Critpt — Epoch AI | Accuracy | 0 |
About
Meta-Llama-3.1-405B-Instruct — a text model from Meta, sold by 6 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. Six 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
- 6
- 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