QwQ-32B-Preview
QwQ is an experimental research model developed by the Qwen Team, designed to advance AI reasoning capabilities.
text → text · made by Alibaba
$0.12→$0.18per Mtok in / out
DeepInfra · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra aggregator | standard | $0.12per Mtok in$0.18per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-09-16 |
Measured 2 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 44thof 54 | Live bench — Epoch AI | Global average | 40.25 |
| 56thof 81 | Forecastbench — Epoch AI | Overall score | 58.3 |
About
QwQ-32B-Preview — a text model from Alibaba, sold by 2 companies from $0.12 in and $0.18 out per million tokens, placed 56th of 81 on Forecastbench — Epoch AI.
It takes text and returns text, with a context window of 32,768 tokens. The catalogue files it under agents. Two companies sell it. The cheapest is $0.12 in and $0.18 out per million tokens at DeepInfra. It has been measured on 2 boards, and stands best at 56th of 81 on Forecastbench — Epoch AI.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Parameters
- 32 billion · read from its own name
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.12 in and $0.18 out per million tokens — DeepInfra
- Boards
- 2
- Best place
- 56th of 81 — Forecastbench — Epoch AI
Known as 1 name
Qwen/QwQ-32B-Preview