Qwen3 30B A3B Instruct 2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.
text → text · made by Alibaba
Sold by 15 ways
| Seller | Lane | Rate |
|---|---|---|
| Nous Research aggregator | standard | $0.048per Mtok in$0.19per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 6 ways | $0.048per Mtok in$0.19per Mtok out | |
| OpenRouter aggregator | standard | $0.048per Mtok in$0.19per Mtok outopenrouter.ai · read 2026-09-13 |
| OpenRouter aggregator | streamlake | $0.048per Mtok in$0.19per Mtok outopenrouter.ai · read 2026-09-10 |
| OpenRouter aggregator | dekallm | $0.09per Mtok in$0.3per Mtok outopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | siliconflow/fp8 | $0.09per Mtok in$0.3per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | coreweave/bf16 | $0.1per Mtok in$0.3per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nebius/fp8 | $0.1per Mtok in$0.3per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | alibaba | $0.13per Mtok in$0.52per Mtok outopenrouter.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.09per Mtok in$0.3per Mtok outmodels.dev · read 2026-09-16 |
| Nebius Token Factory aggregator | standard | $0.1per Mtok in$0.3per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Requesty 2 ways | $0.1per Mtok in$0.3per Mtok out$0.1per Mtok cached | |
| Requesty aggregator | nebius | $0.1per Mtok in$0.3per Mtok out$0.1per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | alibaba | $0.2per Mtok in$0.8per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| ElectronHub aggregator | standard | $0.15per Mtok in$0.3per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Clarifai aggregator | standard | $0.3per Mtok in$0.5per Mtok outmodels.dev · read 2026-09-16 |
| Fireworks AI aggregator | standard | $0.5per Mtok in$0.5per Mtok outraw.githubusercontent.com · read 2026-09-16 |
Measured 6 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 83rdof 123 | Lmca — Epoch AI | Score | 22.37 |
| 96thof 161 | Dtbench — Epoch AI | Accuracy | 67.2 |
| 154thof 290 | OTIS Mock AIME 2024-2025 | mean_score | 62.222 |
| 180thof 222 | Chess puzzles — Epoch AI | mean_score | 2 |
| 216thof 313 | GPQA Diamond | mean_score | 55.619 |
| 480thof 656 | Epoch capabilities index — Epoch AI | ECI Score | 137.44 |
About
Qwen3 30B A3B Instruct 2507 — a text model from Alibaba, sold by 8 companies from $0.048 in and $0.19 out per million tokens, placed 154th of 290 on OTIS Mock AIME 2024-2025.
It takes text and returns text, with a context window of 262,144 tokens. It was published in February 2025. Its sellers say it can call a tool. The catalogue files it under reasoning. Eight companies sell it. The cheapest is $0.048 in and $0.19 out per million tokens at Nous Research. Beside the standard rate there are separately routed and regional lanes. It has been measured on 6 boards, and stands best at 154th of 290 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 262,144 tokens
- Published
- February 2025
- Parameters
- 31 billion
- Licence
- not read
- Sellers
- 8
- Maker's own price
- not read
- Price
- $0.048 in and $0.19 out per million tokens — Nous Research
- Boards
- 6
- Best place
- 154th of 290 — OTIS Mock AIME 2024-2025
Known as 3 names
Qwen/Qwen3-30B-A3B-Instruct-2507alibaba/qwen3-30b-a3b-instruct-2507nebius/qwen/qwen3-30b-a3b-instruct-2507