Qwen (Alibaba)
Alibaba's Qwen family offers a range of models via the DashScope platform, from the flagship Qwen Max to fast and affordable Qwen Turbo. The latest Qwen3 generation adds reasoning capabilities and strong code performance. All models use an OpenAI-compatible API with Bearer auth.
Getting an API Key
- Visit dashscope.console.aliyun.com/apiKey
- Sign in with your Alibaba Cloud account (or create one)
- Generate a new API key (starts with
sk-...) - Paste the key into AISCouncil under Settings > AI Model > Qwen
Qwen does not offer a free tier on the direct DashScope API. All usage is pay-as-you-go. For free access to Qwen models, use OpenRouter which offers Qwen 3 Coder and Qwen 3 Next for free.
API keys are stored locally in your browser (localStorage) and are never included in shared bot URLs.
Supported Models
| Model | Context | Max Output | Input Price | Output Price | Capabilities |
|---|---|---|---|---|---|
| Qwen Max | 32K | 8K | $1.60/MTok | $6.40/MTok | Tools, streaming |
| Qwen Plus | 128K | 8K | $0.40/MTok | $1.20/MTok | Tools, streaming |
| Qwen Turbo | 1M | 8K | $0.05/MTok | $0.20/MTok | Tools, streaming |
| Qwen3 Max | 256K | 64K | $1.20/MTok | $6.00/MTok | Tools, reasoning, streaming |
| Qwen3 Coder | 256K | 64K | $0.22/MTok | $1.00/MTok | Tools, code, streaming |
| Qwen3 Coder Next | 256K | 64K | $0.07/MTok | $0.30/MTok | Tools, code, streaming |
Prices are per million tokens (MTok). See DashScope pricing for the latest rates.
- Qwen3 Max is the latest flagship with reasoning support -- best for complex analysis and hard problems.
- Qwen3 Coder / Coder Next are code specialists -- use them for programming tasks, code review, and generation.
- Qwen Turbo offers an enormous 1M token context window at the lowest price -- ideal for processing long documents cheaply.
Configuration
Select Qwen as the provider when creating a bot profile. The app uses the DashScope international endpoint (dashscope-intl.aliyuncs.com) with OpenAI-compatible format, so no special setup is needed beyond providing your API key.
Tips for Best Results
- Qwen models excel at Chinese language tasks. If your use case involves Chinese text, translation, or cross-lingual work, Qwen is a strong choice.
- Use Qwen Turbo for bulk processing. At $0.05/MTok input with 1M context, it is one of the most cost-effective options for large-scale document analysis.
- Try the Qwen3 Coder models for programming. They offer competitive code generation at very low prices compared to other providers.