Alibaba

Tiny open Qwen code model for lightweight completion and on-device coding

Context

32,768

Output

8,192

Offers

0

Open coding-focused Qwen model for code generation, repair, and repository reasoning

Context

131,072

Output

8,192

Offers

0

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

131,072

Output

8,192

Offers

10

Large open Qwen MoE for multilingual reasoning, coding, and tool use

Context

131,072

Output

16,384

Offers

8

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Context

262,144

Output

16,384

Offers

0

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Context

131,072

Output

16,384

Offers

0

Dense open Qwen model for self-hosted chat, reasoning, and coding

Context

131,072

Output

16,384

Offers

19

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

262,144

Output

65,536

Offers

16

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

262,144

Output

65,536

Offers

14

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

262,144

Output

65,536

Offers

14

Large open Qwen multimodal MoE for visual agents and long technical tasks

Context

262,144

Output

65,536

Offers

25

Qwen instruction model for multilingual chat, reasoning, and tool use

Context

262,144

Output

65,536

Offers

17

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

1,000,000

Output

65,536

Offers

0

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

1,000,000

Output

65,536

Offers

12

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

262,144

Output

65,536

Offers

19

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Context

262,144

Output

65,536

Offers

15

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

1,000,000

Output

65,536

Offers

14

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Context

262,144

Output

65,536

Offers

9

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Context

1,000,000

Output

65,536

Offers

20

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

Context

1,000,000

Output

65,536

Offers

0

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Context

1,000,000

Output

65,536

Offers

22

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

Context

1,000,000

Output

64,000

Offers

17

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Context

262,144

Output

131,072

Offers

0

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

Context

262,144

Output

32,768

Offers

0

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

Context

1,000,000

Output

131,072

Offers

0

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

Context

1,000,000

Output

131,072

Offers

0

Smaller Qwen coder for efficient local agents and repo-level fixes

Context

262,144

Output

65,536

Offers

15

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Context

262,144

Output

65,536

Offers

14

Qwen coding model for software agents, repository edits, and code reasoning

Context

1,000,000

Output

65,536

Offers

7

Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use

Context

262,144

Output

65,536

Offers

0

Hosted Qwen coder for software agents, repo edits, and long-context code

Context

1,048,576

Output

65,536

Offers

11

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Context

262,144

Output

65,536

Offers

15

Qwen instruction model for multilingual chat, reasoning, and tool use

Context

131,072

Output

32,768

Offers

16

Efficient Qwen thinking model for local reasoning, math, and coding agents

Context

131,072

Output

32,768

Offers

13

Qwen vision-language instruct model for visual reasoning, documents, and agent tasks

Context

131,072

Output

32,768

Offers

0

Qwen vision-language thinking model for visual reasoning, documents, and agent tasks

Context

131,072

Output

32,768

Offers

0

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

262,144

Output

32,768

Offers

4

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Context

1,000,000

Output

32,768

Offers

4

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Context

32,768

Output

8,192

Offers

4

Qwen omni model for text, vision, audio, and multimodal agent tasks

Context

32,768

Output

2,048

Offers

3

Qwen instruction model for multilingual chat, reasoning, and tool use

Context

1,000,000

Output

32,768

Offers

7

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Context

1,000,000

Output

16,384

Offers

4

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

131,072

Output

8,192

Offers

2

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

131,072

Output

8,192

Offers

2

Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving

Context

131,072

Output

8,192

Offers

0

Qwen reasoning model for deliberate problem solving, math, and coding

Context

131,072

Output

8,192

Offers

2