Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
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
Qwen vision-language model for visual reasoning, documents, and agent tasks
Open multimodal Qwen MoE for local agents that need vision, audio, and code
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen vision-language model for visual reasoning, documents, and agent tasks
Large open Qwen multimodal MoE for visual agents and long technical tasks
Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use
Qwen vision-language thinking model for visual reasoning, documents, and agent tasks
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks
Efficient Qwen thinking model for local reasoning, math, and coding agents
Qwen instruction model for multilingual chat, reasoning, and tool use
Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use
Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Smaller Qwen coder for efficient local agents and repo-level fixes
Dense open Qwen model for self-hosted chat, reasoning, and coding
Open Qwen coding heavyweight for repository reasoning and agentic engineering
Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving
Open coding-focused Qwen model for code generation, repair, and repository reasoning
Tiny open Qwen code model for lightweight completion and on-device coding
Qwen vision-language model for visual reasoning, documents, and agent tasks
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Qwen3.8 Flash Nextalibaba/qwen3.8-flash-next | 262.144K | $0.12 | $0.4 | 2026-08-27 | |||
| Qwen3.8 27Balibaba/qwen3.8-27b | 262.144K | $0.1 | $0.4 | 2026-08-14 | |||
| Qwen3.8 2.4T A95Balibaba/qwen3.8-2.4t-a95b | 262.144K | $2 | $6 | 2026-08-12 | |||
| Qwen3.6 27Balibaba/qwen3.6-27b | 262.144K | $0.6 | $3.6 | 2026-04-22 | |||
| Qwen3.6 35B-A3Balibaba/qwen3.6-35b-a3b | 262.144K | $0.248 | $1.485 | 2026-04-17 | |||
| Qwen3.5 122B-A10Balibaba/qwen3.5-122b-a10b | 262.144K | $0.4 | $3.2 | 2026-02-23 | |||
| Qwen3.5 27Balibaba/qwen3.5-27b | 262.144K | $0.3 | $2.4 | 2026-02-23 | |||
| Qwen3.5 9Balibaba/qwen3.5-9b | 262.144K | $0.04 | $0.15 | 2026-02-23 | |||
| Qwen3.5 35B-A3Balibaba/qwen3.5-35b-a3b | 262.144K | $0.25 | $2 | 2026-02-23 | |||
| Qwen3.5 397B-A17Balibaba/qwen3.5-397b-a17b | 262.144K | $0.6 | $3.6 | 2026-02-15 | |||
| Qwen3 Coder Nextalibaba/qwen3-coder-next | 262.144K | $0.108 | $0.675 | 2026-02-03 | |||
| Qwen3 VL 235B A22B Thinkingalibaba/qwen3-vl-235b-a22b-thinking | 131.072K | $0.4 | $4 | 2025-09-23 | |||
| Qwen3 VL 235B A22B Instructalibaba/qwen3-vl-235b-a22b-instruct | 131.072K | $0.2 | $0.88 | 2025-09-23 | |||
| Qwen3-Next 80B-A3B (Thinking)alibaba/qwen3-next-80b-a3b-thinking | 131.072K | $0.5 | $6 | 2025-09 | |||
| Qwen3-Next 80B-A3B Instructalibaba/qwen3-next-80b-a3b-instruct | 131.072K | $0.5 | $2 | 2025-09 | |||
| Qwen3 235B-A22B Instruct 2507alibaba/qwen3-235b-a22b-instruct-2507 | 262.144K | $0.069 | $0.455 | 2025-07-21 | |||
| Qwen3 30B A3Balibaba/qwen3-30b-a3b | 131.072K | $0.08 | $0.29 | 2025-04-28 | |||
| Qwen3 235B-A22Balibaba/qwen3-235b-a22b | 131.072K | $0.7 | $2.8 | 2025-04 | |||
| Qwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instruct | 262.144K | $0.45 | $2.25 | 2025-04 | |||
| Qwen3 32Balibaba/qwen3-32b | 131.072K | $0.7 | $2.8 | 2025-04 | |||
| Qwen3-Coder 480B-A35B Instructalibaba/qwen3-coder-480b-a35b-instruct | 262.144K | $1.5 | $7.5 | 2025-04 | |||
| QwQ 32Balibaba/qwq-32b | 131.072K | $0.287 | $0.861 | 2025-03-05 | |||
| Qwen2.5-Coder-32B-Instructalibaba/qwen2.5-coder-32b-instruct | 131.072K | $0.06 | $0.2 | 2024-11-12 | |||
| Qwen2.5-Coder-0.5Balibaba/qwen2.5-coder-0.5b | 32.768K | $0.1 | $0.1 | 2024-11-12 | |||
| Qwen2.5-VL 72B Instructalibaba/qwen2-5-vl-72b-instruct | 131.072K | $2.8 | $8.4 | 2024-09 | |||
| Qwen/Qwen3-Coder-30B-A3B-InstructQwen/Qwen3-Coder-30B-A3B-Instruct | Not documented | — | — | — | |||
| Qwen/Qwen3-VL-235B-A22B-InstructQwen/Qwen3-VL-235B-A22B-Instruct | Not documented | — | — | — | |||
| Qwen/Qwen3-VL-235B-A22B-ThinkingQwen/Qwen3-VL-235B-A22B-Thinking | Not documented | — | — | — | |||
| Qwen/Qwen3-VL-8B-ThinkingQwen/Qwen3-VL-8B-Thinking | Not documented | — | — | — | |||
| Qwen/Qwen3-VL-30B-A3B-InstructQwen/Qwen3-VL-30B-A3B-Instruct | Not documented | — | — | — | |||
| Qwen/Qwen3-VL-30B-A3B-ThinkingQwen/Qwen3-VL-30B-A3B-Thinking | Not documented | — | — | — | |||
| Qwen/Qwen3Guard-Gen-8BQwen/Qwen3Guard-Gen-8B | Not documented | — | — | — | |||
| Qwen/Qwen3Guard-Gen-4BQwen/Qwen3Guard-Gen-4B | Not documented | — | — | — | |||
| Qwen/Qwen-Drive-1.0-4BQwen/Qwen-Drive-1.0-4B | Not documented | — | — | — | |||
| Qwen/Qwen3Guard-Gen-0.6BQwen/Qwen3Guard-Gen-0.6B | Not documented | — | — | — | |||
| Qwen/Qwen3.8-27BQwen/Qwen3.8-27B | Not documented | — | — | — | |||
| Qwen/Qwen-AgentWorld-35B-A3BQwen/Qwen-AgentWorld-35B-A3B | Not documented | — | — | — | |||
| Qwen/Qwen-Image-BenchQwen/Qwen-Image-Bench | Not documented | — | — | — | |||
| Qwen/WebWorld-14BQwen/WebWorld-14B | Not documented | — | — | — | |||
| Qwen/WebWorld-32BQwen/WebWorld-32B | Not documented | — | — | — | |||
| Qwen/WebWorld-8BQwen/WebWorld-8B | Not documented | — | — | — | |||
| Qwen/Qwen3.5-397B-A17BQwen/Qwen3.5-397B-A17B | Not documented | — | — | — | |||
| Qwen/Qwen3.5-122B-A10BQwen/Qwen3.5-122B-A10B | Not documented | — | — | — | |||
| Qwen/Qwen3.5-27BQwen/Qwen3.5-27B | Not documented | — | — | — | |||
| Qwen/Qwen3.6-35B-A3BQwen/Qwen3.6-35B-A3B | Not documented | — | — | — | |||
| Qwen/Qwen3.6-27BQwen/Qwen3.6-27B | Not documented | — | — | — | |||
| Qwen/Qwen3.5-35B-A3BQwen/Qwen3.5-35B-A3B | Not documented | — | — | — | |||
| Qwen/Qwen3.5-9B-BaseQwen/Qwen3.5-9B-Base | Not documented | — | — | — | |||
| Qwen/Qwen3.5-35B-A3B-BaseQwen/Qwen3.5-35B-A3B-Base | Not documented | — | — | — | |||
| Qwen/Qwen3.5-0.8B-BaseQwen/Qwen3.5-0.8B-Base | Not documented | — | — | — |