Meta-Llama-3-70B-Instruct
Model Details Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.
text → text · made by Meta
Sold by 7 ways
| Seller | Lane | Rate |
|---|---|---|
| Databricks 0 ways | $1per Mtok in$3per Mtok out$1per Mtok cached$1per Mtok cache write | |
| Databricks cloudnot on the seller's list today | standard | $1per Mtok in$3per Mtok out$1per Mtok cached$1per Mtok cache writeraw.githubusercontent.com · read 2026-09-22 |
| Microsoft Azure AI cloud | standard | $1.1per Mtok in$0.37per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | standard | $2.65per Mtok in$3.5per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Hyperbolic aggregator | standard | $0.12per Mtok in$0.3per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| DeepInfra aggregator | standard | $0.3per Mtok in$0.4per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Novita AI 0 ways | $0.51per Mtok in$0.74per Mtok out | |
| Novita AI aggregatornot on the seller's list today | standard | $0.51per Mtok in$0.74per Mtok outapi.novita.ai · read 2026-08-25 |
| Featherless AI aggregator | standard | $3.5per Mtok in$8.3per Mtok outapi.featherless.ai · read 2026-09-20 |
Measured 6 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 22ndof 22 | Cybench — Epoch AI | Unguided % Solved | 0.05 |
| 32ndof 217 | Mmlu — Epoch AI | EM | 0.793 |
| 88thof 108 | Math level 5 — Epoch AI | mean_score | 22.555 |
| 205thof 235 | Dtbench — Epoch AI | Accuracy | 54.16 |
| 278thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 4.306 |
| 279thof 326 | GPQA Diamond | mean_score | 40.562 |
About
Meta-Llama-3-70B-Instruct — a text model from Meta, sold by 5 companies from $0.12 in and $0.3 out per million tokens, placed 32nd of 217 on Mmlu — Epoch AI.
It takes text and returns text, with a context window of 8,192 tokens. It was published in April 2024. The catalogue files it under reasoning. Five companies sell it. The cheapest is $0.12 in and $0.3 out per million tokens at Hyperbolic. It has been measured on 6 boards, and stands best at 32nd of 217 on Mmlu — Epoch AI.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 8,192 tokens
- Longest answer
- 8,000 tokens
- Published
- April 2024
- Parameters
- 70 billion · read from its own name
- Licence
- not read
- Sellers
- 5
- Maker's own price
- not read
- Price
- $0.12 in and $0.3 out per million tokens — Hyperbolic
- Boards
- 6
- Best place
- 32nd of 217 — Mmlu — Epoch AI
Known as 8 names
Llama3 70B Instructmeta-llama/Meta-Llama-3-70B-InstructNousResearch/Meta-Llama-3-70B-InstructPrimeIntellect/Meta-Llama-3-70B-Instructpvbhanuteja/Meta-Llama-3-70B-Instructrubra-ai/Meta-Llama-3-70B-Instructv2ray/Llama-3-70B-Instructmeta-llama/llama-3-70b-instruct