QwQ-32B
QwQ is the reasoning model of the Qwen series.
text → text · made by Alibaba
$0.15→$0.4per Mtok in / out
DeepInfra · 7 sellers
Sold by 7 ways
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra aggregator | standard | $0.15per Mtok in$0.4per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Nscale aggregator | standard | $0.18per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Hyperbolic aggregator | standard | $0.2per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| SambaNova Cloud aggregator | standard | $0.5per Mtok in$1per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Cloudflare aggregator | standard | $0.66per Mtok in$1per Mtok outmodels.dev · read 2026-09-16 |
| Fireworks AI aggregator | standard | $0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Together AI aggregator | standard | $1.2per Mtok in$1.2per Mtok outraw.githubusercontent.com · read 2026-09-16 |
Measured 8 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 6thof 54 | Live bench — Epoch AI | Global average | 71.96 |
| 22ndof 49 | Lech mazur writing — Epoch AI | Mean score | 8.02 |
| 56thof 69 | Aider polyglot coding leaderboard | Percent correct | 20.9 |
| 59thof 72 | Aider polyglot — Epoch AI | Percent correct | 20.9 |
| 157thof 222 | Chess puzzles — Epoch AI | mean_score | 5 |
| 161stof 290 | OTIS Mock AIME 2024-2025 | mean_score | 59.167 |
| 194thof 313 | GPQA Diamond | mean_score | 65.341 |
| 477thof 656 | Epoch capabilities index — Epoch AI | ECI Score | 137.62 |
About
QwQ-32B — a text model from Alibaba, sold by 7 companies from $0.15 in and $0.4 out per million tokens, placed 6th of 54 on Live bench — Epoch AI.
It takes text and returns text, with a context window of 131,072 tokens. It was published in November 2024, trained on material up to April 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and code. Seven companies sell it. The cheapest is $0.15 in and $0.4 out per million tokens at DeepInfra. It has been measured on 8 boards, and stands best at 6th of 54 on Live bench — Epoch AI.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 131,072 tokens
- Longest answer
- 32,768 tokens
- Published
- November 2024
- Knowledge to
- April 2024
- Parameters
- 32 billion · read from its own name
- Licence
- not read
- Sellers
- 7
- Maker's own price
- not read
- Price
- $0.15 in and $0.4 out per million tokens — DeepInfra
- Boards
- 8
- Best place
- 6th of 54 — Live bench — Epoch AI
Known as 1 name
Qwen/QwQ-32B