All Products
Search
Document Center

Alibaba Cloud Model Studio:Models

Last Updated:Apr 24, 2026

Choose the right text generation model for AI agents, chatbots, and document processing.

OpenClaw, Claude Code, or Hermes

qwen3.6-plus is ideal for large codebases, offering a balance of performance and cost, full tool calling support, and a 1 million-token context window. Coding Plan users can also select glm-5 or MiniMax-M2.5. All these models are optimized for agent workflows.

Use cases

For chatbots, content generation, summarization, and document processing, we recommend qwen3.6-plus. It offers a good balance of performance and cost, a 1 million-token context window, and built-in tools. Once you've confirmed its performance meets your needs, try qwen3.6-flash to reduce costs. Its performance is close to that of the flagship model, and it supports the same context length and features. If you require the most powerful reasoning capabilities, select qwen3.6-max-preview, which has a higher cost.

Context window

1 million tokens is roughly equivalent to 750,000 English words or about 8 to 10 novels.

  • For long documents or large codebases: qwen3.6-plus / qwen3.6-flash (1 million tokens).

  • For standard tasks: A context window of 128k to 256k tokens is typically sufficient.

For context window details, visit the Models page.

China (Beijing) | Singapore | US | China (Hong Kong) | Frankfurt

Thinking mode

This mode enables step-by-step reasoning, which is ideal for scenarios like multi-step mathematical calculations, code debugging, architecture planning, or legal cross-referencing.

Use the enable_thinking parameter to enable this mode. In the Responses API, the reasoning.effort parameter lets you enable or disable thinking mode and control its depth. All Qwen3 and later models support this feature, most of which operate in a hybrid mode that can be toggled per request.

See Deep thinking.

Function calling and built-in tools

These features allow the model to perform actions, such as querying the weather, searching a database, or booking a meeting.

  • Function calling (custom tools that the model calls): Supported by all general-purpose models.

  • Built-in tools (such as web search, code interpreter, and web scraping) that require no complex configuration.

See Tool calling.

Structured output

This feature ensures that the model returns valid JSON, for example, when extracting names and addresses from text.

See Structured output.

Batch inference

Batch inference is ideal for high-volume, non-latency-sensitive scenarios because it reduces costs.

See Batch inference.

Recommended models

International

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen3.6-max-preview

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3.6-plus

1M

Supported

Supported

Supported

Supported

Supported

qwen3.6-flash

1M

Supported

Supported

Supported

Supported

Supported

Global

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen3.6-max-preview

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3.6-plus

1M

Supported

Supported

Supported

Supported

Unsupported

qwen3.6-flash

1M

Supported

Supported

Supported

Supported

Unsupported

US

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen-plus-us

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen-flash-us

1M

Supported

Supported

Unsupported

Supported

Unsupported

Chinese mainland

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen3.6-max-preview

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3.6-plus

1M

Supported

Supported

Supported

Supported

Supported

qwen3.6-flash

1M

Supported

Supported

Supported

Supported

Supported

kimi-k2.6

256k

Supported

Supported

Unsupported

Unsupported

Unsupported

deepseek-v4-pro

1M

Supported

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-v4-flash

1M

Supported

Supported

Unsupported

Unsupported

Unsupported

Unsupported

glm-5.1

198k

Supported

Supported

Unsupported

Supported

Unsupported

MiniMax-M2.5

192k

Supported

Supported

Unsupported

Unsupported

Unsupported

China (Hong Kong) and EU

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen-plus

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen3.5-flash

1M

Supported

Supported

Supported

Supported

Unsupported

All models

Qwen3.6

Model ID

Context

Max output

Thinking budget

Function Calling

Built-in tools

Structured output

Batch calling

Coding Plan

qwen3.6-max-preview

256k

64k

128k

Supported

Unsupported

Supported

Unsupported

Unsupported

qwen3.6-plus

1M

64k

80k

Supported

Supported

Supported

Unsupported

Supported (Pro only)

qwen3.6-plus-2026-04-02

1M

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.6-flash

1M

64k

128k

Supported

Supported

Supported

Supported

Unsupported

qwen3.6-flash-2026-04-16

1M

64k

128k

Supported

Supported

Supported

Supported

Unsupported

Qwen3.5

Global and Chinese mainland

Model ID

Context

Max output

Thinking budget

Function Calling

Built-in tools

Structured output

Batch calling

Coding Plan

qwen3.5-plus

1M

64k

80k

Supported

Supported

Supported

Unsupported

Supported

qwen3.5-plus-2026-02-15

1M

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-flash

1M

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-flash-2026-02-23

1M

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-397b-a17b

256k

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-122b-a10b

256k

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-27b

256k

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-35b-a3b

256k

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

Hong Kong (China) and EU

Model ID

Context

Max output

Thinking budget

Function Calling

Built-in tools

Structured output

Batch calling

Coding Plan

qwen3.5-flash

1M

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

qwen3.5-flash-2026-02-23

1M

64k

80k

Supported

Supported

Supported

Unsupported

Unsupported

Third-party models

Model ID

Context

Max output

Thinking budget

Function Calling

Built-in tools

Structured output

Batch calling

Coding Plan

deepseek-v4-pro

1M

384k (shared)

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-v4-flash

1M

384k (shared)

Supported

Unsupported

Unsupported

Unsupported

Unsupported

glm-5.1

198k

128k

128k

Supported

Unsupported

Supported

Unsupported

Unsupported

kimi-k2.6

256k

96k

80k

Supported

Unsupported

Unsupported

Unsupported

Supported

MiniMax-M2.5

192k

32k (includes chain-of-thought)

Unsupported

Supported

Unsupported

Unsupported

Unsupported

Supported

Legacy and other models

For new projects, use the Qwen3.6 or Qwen3.5 series. The following models are legacy and no longer recommended. Visit the Models page to view detailed model parameters, such as context window and billing.

China (Beijing) | Singapore | United States | China (Hong Kong) | Germany (Frankfurt)

View legacy and other models

Qwen3

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen3-max

256k

Supported

Supported

Supported

Supported

Supported

qwen3-max-2026-01-23

256k

Supported

Supported

Supported

Supported

Unsupported

qwen3-max-preview

256k

Supported

Supported

Supported

Supported

Unsupported

qwen3-max-2025-09-23

256k

Supported

Supported

Supported

Supported

Unsupported

qwen3-235b-a22b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-235b-a22b-thinking-2507

256k

Supported

Supported

Unsupported

Unsupported

Unsupported

qwen3-235b-a22b-instruct-2507

256k

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen3-next-80b-a3b-thinking

256k

Supported

Supported

Unsupported

Unsupported

Unsupported

qwen3-next-80b-a3b-instruct

256k

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen3-32b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-30b-a3b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-30b-a3b-thinking-2507

256k

Supported

Supported

Unsupported

Unsupported

Unsupported

qwen3-30b-a3b-instruct-2507

256k

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen3-14b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-8b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-4b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-1.7b

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-0.6b

256k

Supported

Supported

Unsupported

Supported

Unsupported

Qwen3-Coder

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen3-coder-plus

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-plus-2025-09-23

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-plus-2025-07-22

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-flash

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-flash-2025-07-28

1M

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-next

256k

Supported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-480b-a35b-instruct

256k

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen3-coder-30b-a3b-instruct

256k

Unsupported

Supported

Unsupported

Supported

Unsupported

Qwen2.5 (open source)

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen2.5-omni-7b

1M

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen2.5-vl-72b-instruct

1M

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen2.5-vl-32b-instruct

1M

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen2.5-vl-7b-instruct

1M

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen2.5-vl-3b-instruct

1M

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen2.5-72b-instruct

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen2.5-72b-instruct-1m

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen2.5-32b-instruct

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen2.5-14b-instruct

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen2.5-14b-instruct-1m

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen2.5-7b-instruct

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

qwen2.5-7b-instruct-1m

1M

Unsupported

Supported

Unsupported

Supported

Unsupported

Translation

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen-mt-plus

16k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen-mt-turbo

16k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen-mt-flash

16k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen-mt-lite

16k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

Qwen-Long

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen-long

10M

Unsupported

Unsupported

Unsupported

Supported

Supported

qwen-long-latest

10M

Unsupported

Unsupported

Unsupported

Supported

Supported

qwen-long-2025-01-25

10M

Unsupported

Unsupported

Unsupported

Supported

Unsupported

Role-playing

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen-plus-character

32k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen-plus-character-ja

32k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

qwen-flash-character

8k

Unsupported

Unsupported

Unsupported

Unsupported

Unsupported

Legacy Qwen

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

qwen-plus and its snapshots

1M

Supported

Supported

Supported

Supported

Supported

qwen-max and its snapshots

128k

Supported

Supported

Supported

Supported

Supported

qwen-flash and its snapshots

1M

Supported

Supported

Supported

Supported

Supported

qwen-turbo and its snapshots

1M

Supported

Supported

Supported

Supported

Supported

qwq-plus

128k

Supported

Supported

Unsupported

Unsupported

Supported

qvq-max and its snapshots

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported

qwen-omni-turbo and its snapshots

32k

Unsupported

Unsupported

Unsupported

Unsupported

Supported

Third-party models

Model

Context

Thinking mode

Function Calling

Built-in tools

Structured output

Batch calling

glm-5

198k

Supported

Supported

Unsupported

Supported

Unsupported

glm-4.7

198k

Supported

Supported

Unsupported

Supported

Unsupported

glm-4.5

198k

Supported

Supported

Unsupported

Supported

Unsupported

glm-4.5-air

198k

Supported

Supported

Unsupported

Supported

Unsupported

MiniMax-M2.1

200k

Supported

Supported

Unsupported

Unsupported

Unsupported

kimi-k2.5

256k

Supported

Supported

Unsupported

Unsupported

Unsupported

kimi-k2-thinking

256k

Supported

Supported

Unsupported

Supported

Unsupported

Moonshot-Kimi-K2-Instruct

256k

Unsupported

Supported

Unsupported

Unsupported

Unsupported

deepseek-v3.2

128k

Supported

Supported

Unsupported

Unsupported

Unsupported

deepseek-v3.2-exp

128k

Supported

Supported

Unsupported

Unsupported

Unsupported

deepseek-v3.1

128k

Supported

Supported

Unsupported

Unsupported

Unsupported

deepseek-v3

128k

Unsupported

Supported

Unsupported

Unsupported

Supported

deepseek-r1

128k

Supported

Supported

Unsupported

Unsupported

Supported

deepseek-r1-0528

128k

Supported

Supported

Unsupported

Unsupported

Unsupported

deepseek-r1-distill-llama-70b

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-r1-distill-qwen-32b

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-r1-distill-qwen-14b

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-r1-distill-qwen-7b

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-r1-distill-qwen-1.5b

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported

deepseek-r1-distill-llama-8b

128k

Supported

Unsupported

Unsupported

Unsupported

Unsupported