Qwen3.5 35B-A3BOpen weights
Alibaba · released 2026-02-23
The official API price of Qwen3.5 35B-A3B is $0.25 per 1M input tokens and $2 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 65.5K output tokens per request. 21 providers sell it. The lowest is AIHubMix: $0.0564 input, $0.4512 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| AlibabaOfficialqwen3.5-35b-a3b | $0.25 | $2 | — | Official | Official docs |
 AIHubMixLowestTiered pricingqwen3.5-35b-a3b | $0.0564 | $0.4512 | — | LowestTiered pricing | Official docs |
 EmpirioLabs AITiered pricingqwen3-5-35b-a3b | $0.057 | $0.459 | $0.057 | Tiered pricing | Official docs |
MMerge Gatewayqwen/ | $0.057 | $0.459 | $0.020357 | Official docs | |
OOrcaRouterTiered pricingqwen/ | $0.057 | $0.459 | — | Tiered pricing | Official docs |
3302.AITiered pricingqwen3.5-35b-a3b | $0.06 | $0.46 | — | Tiered pricing | Official docs |
 SiliconFlow (China)Tiered pricingQwen/ | $0.059779 | $0.478232 | — | Tiered pricing | Official docs |
 Deep InfraQwen/ | $0.14 | $1 | $0.05 | Official docs | |
NNanoGPTqwen/ | $0.14 | $1 | $0.05 | Official docs | |
NNanoGPTqwen/ | $0.14 | $1 | $0.05 | Official docs | |
 OpenRouterqwen/ | $0.14 | $1 | $0.05 | Official docs | |
RRequestyqwen3.5-35b-a3b | $0.14 | $1 | $0.05 | Official docs |
11 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Venice AIqwen3-5-35b-a3b | $0.15 | $1 | $0.05 | Official docs | |
KKilo Gatewayqwen/ | $0.1625 | $1.3 | — | Official docs | |
MMixlayerqwen/ | $0.25 | $1.3 | — | Official docs | |
| SiliconFlowQwen/ | $0.24 | $1.8 | $0.15 | Official docs | |
OOfoxbailian/ | $0.29 | $1.83 | $0.29 | Official docs | |
OOfoxqwen/ | $0.29 | $1.83 | $0.29 | Official docs | |
 Hugging FaceQwen/ | $0.25 | $2 | — | Official docs | |
JJalapeno CloudQwen3.5-35B-A3B | $0.25 | $2 | — | Official docs | |
 DevPass (LLM Gateway)qwen3.5-35b-a3b | $0.25 | $2 | — | Official docs | |
LLLM Gatewayalibaba/ | $0.25 | $2 | — | Official docs | |
 Novita AIqwen/ | $0.25 | $2 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Qwen vision-language model for visual reasoning, documents, and agent tasks
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 65.5K
- Input
- Text, Image, Video
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-01
- Open weights
- Yes
- Released
- 2026-02-23
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.