Qwen3.5 35B-A3B: API pricing, providers and specs
Qwen3.5 35B-A3B is a text model by Alibaba. 19 providers serve it, from $0.451 to $2 /1M; the lowest price is at AIHubMix.
A newer version is out: Qwen3.6 35B-A3B · released Apr 15, 2026
How Qwen3.5 35B-A3B compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.451 /1M, its lowest price undercuts 68% of comparable models (median $1.10).
- Its 262K-token context window is larger than 45% of them (median 262K), about 390 pages of text.
- On LMArena's Text board it ranks #45 of the 120 comparable models scored there.
- 19 providers serve it; 87% of comparable models have fewer.
- Its weights are open under the Apache 2.0 license: commercial use allowed.
Qwen3.5 35B-A3B prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 AIHubMix | $0.056/1M | From$0.451/1M | — | 262K |
 OrcaRouter | $0.057/1M | $0.459/1M | — | 33K |
 EmpirioLabs AI | $0.057/1M | From$0.459/1M | $0.057/1M | 256K |
 APIYI | $0.06/1M | $0.48/1M | — | — |
 LaoZhang API | $0.06/1M | $0.48/1M | — | — |
 Venice AI | $0.15/1M | $1/1M | $0.05/1M | — |
 Hugging Face | $0.14/1M | From$1/1M | — | — |
 Deep Infra | $0.14/1M | From$1/1M | $0.05/1M | — |
| OpenRouter | $0.14/1M | From$1/1M | $0.05/1M | 262K |
 Requesty | $0.14/1M | From$1/1M | $0.05/1M | 262K |
 Prime Inference | $0.25/1M | $1.30/1M | — | — |
 SiliconFlow | $0.222/1M | $1.78/1M | — | — |
| SiliconFlow | $0.24/1M | $1.80/1M | $0.15/1M | — |
| Atlas Cloud | $0.225/1M | $1.80/1M | — | — |
 Ofox | $0.29/1M | $1.83/1M | $0.29/1M | 256K |
| AlibabaOfficial | $0.25/1M | From$2/1M | — | — |
 Novita AI | $0.25/1M | $2/1M | — | — |
| DevPass (LLM Gateway) | $0.25/1M | From$2/1M | — | — |
 Jiekou.AI | $0.25/1M | $2/1M | — | — |
- AIHubMixFrom$0.451
- OrcaRouter$0.459
- EmpirioLabs AIFrom$0.459
- APIYI$0.48
- LaoZhang API$0.48
- Venice AI$1
- Hugging FaceFrom$1
- Deep InfraFrom$1
- OpenRouterFrom$1
- RequestyFrom$1
- Prime Inference$1.30
- SiliconFlow$1.78
Specs
- Type
- Text
- Maker
- Alibaba
- Inputs
- Image, Text, Video
- Outputs
- Text
- Context
- 262K≈ 390 pages of text
- Max output
- 82K
- Capabilities
- JSON, Reasoning, Tool calling, Vision
- Released
- Feb 24, 2026
- License
- Apache 2.0commercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 36B
- Arena score
- 1395Text
- Monthly searches
- 3K
1 uncensored versions · See them
Alternatives to Qwen3.5 35B-A3B
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Qwen3.5 35B-A3Bthis model | $0.451/1M | 262K | 1395 | 19 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
| GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
 Sonar | $1/1M | 127K | — | 9 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
 MiMo-V2.6-Pro | $0.696/1M | 1.05M | 1625 | 21 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
More from Alibaba
Qwen-Image-2.1Alibaba$0.02/imgQwen3.8 2.4T A95BAlibaba$4.11/1MWan3.0Alibaba$0.025/secQwen3.8 27BAlibaba$0.50/1MWan 2.2Alibaba$0.01/runQwen3.8 Flash NextAlibaba$0.376/1MQwen2-1.5B-InstructAlibaba$0.20/1MQwen3.5 FlashAlibaba$0.287/1MQwen3.5 35B-A3B FAQ
AIHubMix, at $0.451 /1M. 19 providers serve Qwen3.5 35B-A3B; the table above lists every one with its price.
Qwen3.5 35B-A3B reads up to 262K tokens per request and writes up to 82K.
Yes. Qwen3.5 35B-A3B's weights can be downloaded from its maker's Hugging Face page, under the Apache 2.0 license.
About 36B, as the safetensors metadata of its official Hugging Face repo states.
19 API providers serve Qwen3.5 35B-A3B. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us