Qwen3.6 35B A3B
Qwen3.6 35B A3B is a model by Alibaba for reasoning and writing code, it stands 16th of 17 on SWE-rebench Leaderboard, and 13 sellers in the catalogue publish a price for it.
text + image + video → text · made by Alibaba
$0.1→$0.95per Mtok in / out
DeepInfra · 13 sellers
Sold by 27 ways
| Seller | Lane | Rate |
|---|---|---|
| Thinking Machines Lab api | training | $0.54per Mtok in$1.33per Mtok out$0.11per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| OpenRouter 11 ways | $0.1per Mtok in$0.9per Mtok out$0.025per Mtok cached | |
| OpenRouter aggregator | darkbloom/fp4 | $0.05per Mtok in$0.7per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-09-20 |
| OpenRouter aggregator | standard | $0.1per Mtok in$0.9per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-10-20 |
| OpenRouter aggregator | akashml/fp8 | $0.1per Mtok in$0.9per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | coreweave/fp8 | $0.1per Mtok in$0.95per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-10-27 |
| OpenRouter aggregator | deepinfra/fp8 | $0.1per Mtok in$0.95per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | dekallm | $0.1per Mtok in$1per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | parasail/fp8 | $0.1per Mtok in$0.9per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-10-20 |
| OpenRouter aggregatornot on the seller's list today | reka | $0.1per Mtok in$1per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-09-27 |
| OpenRouter aggregator | venice/fp8 | $0.1per Mtok in$1per Mtok outopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregatornot on the seller's list today | io-net/fp8 | $0.19per Mtok in$0.99per Mtok out$0.099per Mtok cachedopenrouter.ai · read 2026-09-17 |
| OpenRouter aggregator | phala | $0.2per Mtok in$1.27per Mtok out$0.056per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | siliconflow/fp8 | $0.24per Mtok in$1.8per Mtok out$0.15per Mtok cachedopenrouter.ai · read 2026-09-11 |
| OpenRouter aggregator | atlas-cloud/fp8 | $0.25per Mtok in$1.25per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-10-17 |
| DeepInfra aggregator | standard | $0.1per Mtok in$0.95per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 3 ways | $0.15per Mtok in$0.95per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.1per Mtok in$0.95per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.15per Mtok in$0.95per Mtok outmodels.dev · read 2026-11-01 |
| Hugging Face Inference Providers aggregator | scaleway | $0.28per Mtok in$1.71per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nous Research aggregator | standard | $0.1per Mtok in$0.9per Mtok out$0.025per Mtok cachedinference-api.nousresearch.com · read 2026-10-29 |
| Venice AI aggregator | standard | $0.1per Mtok in$1per Mtok outmodels.dev · read 2026-11-01 |
| ElectronHub aggregator | standard | $0.15per Mtok in$1per Mtok outapi.electronhub.ai · read 2026-11-01 |
| AtlasCloud aggregator | standard | $0.19per Mtok in$1.11per Mtok out$0.19per Mtok cachedapi.atlascloud.ai · read 2026-09-20 |
| Featherless AI aggregator | standard | $0.19per Mtok in$1.11per Mtok outapi.featherless.ai · read 2026-09-20 |
| RedPill aggregator | standard | $0.2per Mtok in$1.27per Mtok out$0.056per Mtok cachedapi.redpill.ai · read 2026-09-20 |
| SiliconFlow aggregator | standard | $0.24per Mtok in$1.8per Mtok out$0.15per Mtok cachedmodels.dev · read 2026-11-01 |
| Novita AI aggregator | standard | $0.25per Mtok in$1.49per Mtok outapi.novita.ai · read 2026-08-25 |
| PPIO aggregator | standard | $1.8per Mtok in$10.8per Mtok outapi.ppinfra.com · read 2026-11-01 |
Measured 15 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 16thof 17 | SWE-rebench Leaderboard (default window 15/05/2026–01/07/2026, 111 problems) | Resolved Rate (%) | 24.7 |
| 22ndof 29 | Surface evolver bench — Epoch AI | Mean score | 0.444 |
| 57thof 142 | Mystery game puzzles — Epoch AI | mean_score (none) | 22 |
| 84thof 131 | Artificial Analysis · Agentic Index | Index | 13.1 |
| 91stof 122 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (none) | 20.351 |
| 93rdof 306 | OTIS Mock AIME 2024-2025 | mean_score | 86.667 |
| 102ndof 326 | GPQA Diamond | mean_score (none) | 84.848 |
| 107thof 163 | Artificial Analysis · Coding Index | Index | 41.9 |
| 125thof 135 | Webdev arena — Epoch AI | Arena Score | 1250.15 |
| 137thof 197 | Lmca — Epoch AI | Score | 29.7 |
| 144thof 173 | Weirdml — Epoch AI | Accuracy | 34.49 |
| 155thof 235 | Dtbench — Epoch AI | Accuracy | 73.87 |
| 158thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.246 |
| 189thof 260 | Critpt — Epoch AI | Accuracy | 0.286 |
| 200thof 235 | Scicode — Epoch AI | Score | 36.574 |
About
Qwen3.6 35B A3B — a text model from Alibaba, sold by 13 companies from $0.1 in and $0.95 out per million tokens, placed 93rd of 306 on OTIS Mock AIME 2024-2025.
It takes text, images and video and returns text, with a context window of 32,768 tokens. It was published in April 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 reasoning and code. Thirteen companies sell it. The cheapest is $0.1 in and $0.95 out per million tokens at DeepInfra. Beside the standard rate there are separately routed and regional lanes. It has been measured on 15 boards, and stands best at 93rd of 306 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image + video
- Returns
- text
- Context
- 32,768 tokens
- Published
- April 2026
- Knowledge to
- April 2025
- Parameters
- 36 billion
- Licence
- not read
- Sellers
- 13
- Maker's own price
- not read
- Price
- $0.1 in and $0.95 out per million tokens — DeepInfra
- Boards
- 15
- Best place
- 93rd of 306 — OTIS Mock AIME 2024-2025
Known as 2 names
Qwen3.6-35B-A3Bqwen/qwen3.6-35b-a3b