Llama 3 70B
A 70-billion-parameter Meta Llama 3 auto-regressive language model using an optimized transformer with Grouped-Query Attention, intended for commercial and research use in English, in pretrained and instruction-tuned chat variants.
text → text + code · made by Meta
Sold by 3 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock 0 ways | $2.65per Mtok in$3.5per Mtok out | |
| AWS Bedrock cloudnot on the seller's list today | standard | $2.65per Mtok in$3.5per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
| ElectronHub aggregator | standard | $0.6per Mtok in$0.8per Mtok outapi.electronhub.ai · read 2026-10-31 |
| Featherless AI aggregator | standard | $3.5per Mtok in$8.3per Mtok outapi.featherless.ai · read 2026-09-20 |
Measured 2 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 12thof 137 | Wino grande — Epoch AI | Accuracy | 83.5 |
| 78thof 92 | Forecastbench — Epoch AI | Overall score | 60.2 |
About
Llama 3 70B — a text and code model from Meta, sold by 2 companies from $0.6 in and $0.8 out per million tokens, placed 12th of 137 on Wino grande — Epoch AI.
It takes text and returns text and code, with a context window of 8,192 tokens. The catalogue files it under code and agents. Two companies sell it. The cheapest is $0.6 in and $0.8 out per million tokens at ElectronHub. It has been measured on 2 boards, and stands best at 12th of 137 on Wino grande — Epoch AI.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text
- Returns
- text + code
- Context
- 8,192 tokens
- Parameters
- 70 billion · read from its own name
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.6 in and $0.8 out per million tokens — ElectronHub
- Boards
- 2
- Best place
- 12th of 137 — Wino grande — Epoch AI
Known as 3 names
NousResearch/Meta-Llama-3-70Bmeta-llama/Meta-Llama-3-70Bv2ray/Llama-3-70B