Qwen3 30B A3B Thinking 2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking.
text → text · made by Alibaba
Sold by 4 ways
| Seller | Lane | Rate |
|---|---|---|
| Nous Research aggregator | standard | $0.2per Mtok in$2.4per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter aggregator | standard | $0.2per Mtok in$2.4per Mtok outopenrouter.ai · read 2026-08-24 |
| Clarifai aggregator | standard | $0.36per Mtok in$1.3per 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 |
Measured 12 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 87thof 161 | Dtbench — Epoch AI | Accuracy | 69.33 |
| 88thof 123 | Lmca — Epoch AI | Score | 19.53 |
| 131stof 143 | Artificial Analysis · Agentic Index | Index | 0.9 |
| 132ndof 290 | OTIS Mock AIME 2024-2025 | mean_score | 70.278 |
| 134thof 177 | Critpt — Epoch AI | Accuracy | 0.286 |
| 140thof 222 | Chess puzzles — Epoch AI | mean_score | 8 |
| 146thof 152 | Design Arena · dataviz (models) | Elo | 940 |
| 146thof 168 | Scicode — Epoch AI | Score | 33.333 |
| 154thof 162 | Design Arena · website (models) | Elo | 943 |
| 168thof 184 | Artificial Analysis · Coding Index | Index | 12.1 |
| 175thof 313 | GPQA Diamond | mean_score | 70.076 |
| 450thof 656 | Epoch capabilities index — Epoch AI | ECI Score | 139.66 |
About
Qwen3 30B A3B Thinking 2507 — a text model from Alibaba, sold by 4 companies from $0.2 in and $2.4 out per million tokens, placed 132nd of 290 on OTIS Mock AIME 2024-2025.
It takes text and returns text, with a context window of 81,920 tokens. It was published in July 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under evaluate and reasoning. Four companies sell it. The cheapest is $0.2 in and $2.4 out per million tokens at Nous Research. It has been measured on 12 boards, and stands best at 132nd of 290 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 81,920 tokens
- Published
- July 2025
- Parameters
- 31 billion
- Licence
- not read
- Sellers
- 4
- Maker's own price
- not read
- Price
- $0.2 in and $2.4 out per million tokens — Nous Research
- Boards
- 12
- Best place
- 132nd of 290 — OTIS Mock AIME 2024-2025
Known as 1 name
qwen/qwen3-30b-a3b-thinking-2507