China AI Hub
API / model-studio
model-studio API
Provider: alibaba-cloud · Type: official
model-studio is an API by alibaba-cloud, served at https://dashscope-us.aliyuncs.com/compatible-mode/v1 for official models, exposing Qwen3.8-2.4T-A95B, Qwen3.8-Max, Qwen3.8-Flash.
| Key fact | Value |
|---|---|
| Endpoint | https://dashscope-us.aliyuncs.com/compatible-mode/v1 |
| Authentication | API key (DASHSCOPE_API_KEY), created in the Model Studio console; keys are region-bound |
| Streaming | Yes |
| Function calling | Yes |
| Tool calling | Yes |
| Structured output | Yes |
| Vision | Yes |
| Audio | Unknown |
| Rate limits | Global regions (Frankfurt / US / Tokyo / Hong Kong): 30,000 RPM, 5,000,000 TPM for qwen3.8-max and qwen3.8-flash; Beijing and Singapore limits are dynamic, tiered by monthly spend |
| Regions | china-beijing, singapore, hong-kong, japan-tokyo, us-virginia, germany-frankfurt |
| Cloud providers | Alibaba Cloud |
| Documentation | https://www.alibabacloud.com/help/en/model-studio/ |
Context limits
| Model | Input limit | Output limit |
|---|---|---|
| qwen3.8-max | 991,808 | 131,072 |
| qwen3.8-flash | 991,808 | 131,072 |
Alibaba Cloud Model Studio (Bailian) serves the Qwen family through OpenAI-compatible Chat Completions
and Responses APIs (qwen3.8-flash also supports the Anthropic protocol). Regional base URLs follow the
pattern https://{WorkspaceId}.{region}.maas.aliyuncs.com/compatible-mode/v1 for Singapore, Beijing,
Hong Kong and Tokyo; the US endpoint is https://dashscope-us.aliyuncs.com/compatible-mode/v1.
Authentication uses a region-bound API key. Streaming is supported (stream_options include_usage for
token counts). Thinking is toggled with enable_thinking; structured outputs, function calling, web
search, prefix completion, context caching and (Beijing-only) batch inference are available on
supported models. A managed API product also exists at qwencloud.com.
Provider
Models served
Pricing
Sources
Data interpretation
| Field | Value | Evidence type |
|---|---|---|
| Endpoint | https://dashscope-us.aliyuncs.com/compatible-mode/v1 | Official |
| Authentication | API key (DASHSCOPE_API_KEY), created in the Model Studio console; keys are region-bound | Official |
| Capabilities | Streaming, Function calling, Tool calling, Structured output, Vision | Official |
| Models served | 3 models in the database | China AI Hub analysis |
Evidence types: Official = vendor documentation or official pages. China AI Hub analysis = derived from the database itself. See the sourcing policy.
What is the model-studio API endpoint?
The model-studio API endpoint is https://dashscope-us.aliyuncs.com/compatible-mode/v1.
How do you authenticate with the model-studio API?
API key (DASHSCOPE_API_KEY), created in the Model Studio console; keys are region-bound.
What are the context limits of the model-studio API?
qwen3.8-max: 991,808 in / 131,072 out; qwen3.8-flash: 991,808 in / 131,072 out.
Does the model-studio API support function calling?
Yes — the model-studio API supports function calling.
Where does China AI Hub get its model-studio API data?
From 3 sources, last verified 2026-09-20.