Qwen2-72B-Instruct
The 72 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.
text → text · made by Alibaba
$0.35→$0.4per Mtok in / out
DeepInfra · 4 sellers
Sold by 4 ways
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra aggregator | standard | $0.35per Mtok in$0.4per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Together AI aggregator | standard | $0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Featherless AI aggregator | standard | $12per Mtok in$20per Mtok outapi.featherless.ai · read 2026-09-20 |
Measured 6 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 16thof 16 | The agent company — Epoch AI | % Score | 0.042 |
| 21stof 217 | Mmlu — Epoch AI | EM | 0.824 |
| 42ndof 49 | Metr time horizons — Epoch AI | average_score | 0.299 |
| 75thof 108 | Math level 5 — Epoch AI | mean_score | 39.067 |
| 166thof 173 | Weirdml — Epoch AI | Accuracy | 11.3 |
| 277thof 326 | GPQA Diamond | mean_score | 40.783 |
About
Qwen2-72B-Instruct — a text model from Alibaba, sold by 4 companies from $0.35 in and $0.4 out per million tokens, placed 21st of 217 on Mmlu — Epoch AI.
It takes text and returns text, with a context window of 32,768 tokens. The catalogue files it under reasoning and agents. Four companies sell it. The cheapest is $0.35 in and $0.4 out per million tokens at DeepInfra. It has been measured on 6 boards, and stands best at 21st of 217 on Mmlu — Epoch AI.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Parameters
- 72 billion · read from its own name
- Licence
- not read
- Sellers
- 4
- Maker's own price
- not read
- Price
- $0.35 in and $0.4 out per million tokens — DeepInfra
- Boards
- 6
- Best place
- 21st of 217 — Mmlu — Epoch AI
Known as 1 name
Qwen/Qwen2-72B-Instruct