Providers
bail (Qwen)
Alibaba Bailian — Qwen-2.5/3 + Qwen-VL via the DashScope OpenAI-compatibility endpoint.
import { bail } from '@agentskit/adapters'
const adapter = bail({
apiKey: process.env.DASHSCOPE_API_KEY!,
model: 'qwen-max',
})qwen is exported as an alias for the same factory.
#Options
| Option | Type | Default |
|---|---|---|
apiKey | string | required |
model | string | qwen-max |
baseUrl | string | https://dashscope.aliyuncs.com/compatible-mode/v1 |
retry | RetryOptions | inherited |
#Capabilities
{ streaming: true, tools: true, multiModal: true, usage: true }. The compat endpoint mirrors the OpenAI chat-completions schema, so request/response shapes match openai({ baseUrl }).
#Why bail / Qwen
- APAC latency + data residency.
- Qwen-VL handles image / audio / video inputs.
- Strong Chinese-first reasoning.
#Env
| Var | Purpose |
|---|---|
DASHSCOPE_API_KEY | API key |