Qwen3.5 9B
Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture.
text + image + video → text · made by Alibaba
Sold by 21 ways
| Seller | Lane | Rate |
|---|---|---|
| Thinking Machines Lab api | training | $0.66per Mtok in$2per Mtok out$0.13per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| OpenRouter 7 ways | $0.17per Mtok in$0.25per Mtok out$0.04per Mtok cached | |
| OpenRouter aggregator | primeintellect/bf16 | $0.017per Mtok in$0.025per Mtok out$0.015per Mtok cachedopenrouter.ai · read 2026-11-01 |
| OpenRouter aggregator | darkbloom/fp4 | $0.08per Mtok in$0.13per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-09-20 |
| OpenRouter aggregator | deepinfra/bf16 | $0.1per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-10-21 |
| OpenRouter aggregator | parasail/bf16 | $0.1per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | siliconflow/fp8 | $0.1per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-10-21 |
| OpenRouter aggregator | standard | $0.17per Mtok in$0.25per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-10-24 |
| OpenRouter aggregatornot on the seller's list today | batch | $0.17per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | together | $0.17per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-25 |
| Requesty aggregator | runware | $0.09per Mtok in$0.13per Mtok out$0.009per Mtok cachedrouter.requesty.ai · read 2026-09-20 |
| DeepInfra aggregator | standard | $0.1per Mtok in$0.15per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 3 ways | $0.17per Mtok in$0.25per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.1per Mtok in$0.15per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | ovhcloud | $0.12per Mtok in$0.18per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.17per Mtok in$0.25per Mtok outmodels.dev · read 2026-11-01 |
| Hugging Face Inference Providers aggregatornot on the seller's list today | together | $0.17per Mtok in$0.25per Mtok outrouter.huggingface.co · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.1per Mtok in$0.15per Mtok outmodels.dev · read 2026-11-01 |
| Venice AI 0 ways | $0.1per Mtok in$0.15per Mtok out | |
| Venice AI aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.15per Mtok outmodels.dev · read 2026-10-20 |
| Featherless AI aggregator | standard | $0.17per Mtok in$0.25per Mtok outapi.featherless.ai · read 2026-09-20 |
| Nous Research aggregator | standard | $0.17per Mtok in$0.25per Mtok out$0.04per Mtok cachedinference-api.nousresearch.com · read 2026-10-29 |
| Nous Research aggregatornot on the seller's list today | batch | $0.17per Mtok in$0.25per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| Together AI aggregator | standard | $0.17per Mtok in$0.25per Mtok outmodels.dev · read 2026-11-01 |
Measured 9 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 113thof 131 | Artificial Analysis · Agentic Index | Index | 1.2 |
| 123rdof 163 | Artificial Analysis · Coding Index | Index | 28.7 |
| 138thof 326 | GPQA Diamond | mean_score | 78.977 |
| 153rdof 197 | Lmca — Epoch AI | Score | 24.47 |
| 158thof 235 | Dtbench — Epoch AI | Accuracy | 71.2 |
| 173rdof 306 | OTIS Mock AIME 2024-2025 | mean_score (none) | 61.667 |
| 186thof 260 | Critpt — Epoch AI | Accuracy (none) | 0.571 |
| 194thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.092 |
| 217thof 235 | Scicode — Epoch AI | Score | 29.514 |
About
Qwen3.5 9B — a text model from Alibaba, sold by 9 companies from $0.1 in and $0.15 out per million tokens, placed 138th of 326 on GPQA Diamond.
It takes text, images and video and returns text, with a context window of 32,768 tokens. It was published in February 2026, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under extract and reasoning. Nine companies sell it. The cheapest is $0.1 in and $0.15 out per million tokens at DeepInfra. Beside the standard rate there are separately routed and regional lanes. It has been measured on 9 boards, and stands best at 138th of 326 on GPQA Diamond.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image + video
- Returns
- text
- Context
- 32,768 tokens
- Published
- February 2026
- Knowledge to
- April 2025
- Parameters
- 9.7 billion
- Licence
- not read
- Sellers
- 9
- Maker's own price
- not read
- Price
- $0.1 in and $0.15 out per million tokens — DeepInfra
- Boards
- 9
- Best place
- 138th of 326 — GPQA Diamond
Known as 4 names
Qwen3.5-9BQwen/Qwen3.5-9Bunsloth/Qwen3.5-9Brunware/qwen3.5-9b