Qwen vision-language model for visual reasoning, documents, and agent tasks
https://api-inference.modelscope.cn/v1 qwen-qwen3-5-35b-a3b Qwen3.5-35B-A3B is listed for chat workloads and supports a 131K context window.
Check ModelScope's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this qwen3-5-35b-a3b listing on ModelScope in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Qwen/Qwen3.5-35B-A3B | Check provider | 131K | OpenAI-style | 2,000 RPD total; <=500 RPD/model (dynamic) |
| Model | Provider | Context | Access |
|---|---|---|---|
| Qwen/Qwen3.5-27B | ModelScope | 131K | Check provider |
| MiniMax-M2.5-highspeed | ModelScope | 205K | Check provider |
| Kimi K2.5 | ModelScope | 262K | Check provider |
| Qwen/Qwen-Image | ModelScope | 131K | Check provider |
| deepseek-ai/DeepSeek-V3.2 | ModelScope | 8K | Check provider |
Qwen3.5-35B-A3B is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Qwen3.5-35B-A3B appears in the free model catalog for ModelScope, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is qwen-qwen3-5-35b-a3b.
The listed free tier limit is 2,000 RPD total; <=500 RPD/model (dynamic). Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 131K tokens with up to 131K output tokens.
Qwen3.5 35B (A3B active via MoE) is Alibaba's latest mid-size model, available free on ModelScope's inference API. With 131K context and the efficient 3B active parameters, it delivers strong performance at low inference cost. ModelScope's API is not OpenAI-compatible by default; check ModelScope documentation for the correct request format. Best for developers in the Chinese AI ecosystem or those evaluating Qwen's latest generation.
For API keys, setup steps, and provider-level limits, see the ModelScope provider page.