Qwen
Qwen3.5 Plus
active balanced
Qwen3.5 series balanced model. Text/image/video input. 1M context, faster and cheaper than Qwen3-Max.
Context 1M
Max output 32K
Pricing /1M tok $0.11 / $0.67 • API
Released Mar 1, 2026
// provider_directory
Qwen
All tracked Qwen models — pricing, context windows, lifecycle state, and release history in one place.
9 tracked models
8 live or preview
9 with listed pricing
Mar 1, 2026 latest release
// model_index
All Qwen models
Qwen
Qwen3.5 Flash
active fast
Qwen3.5 speed model. 1M context, lowest cost in Qwen lineup.
Context 1M
Max output 32K
Pricing /1M tok $0.03 / $0.28 • API
Released Mar 1, 2026
Qwen
Qwen3 Max
active frontier
Alibaba's flagship Qwen model. 262K context. Supports thinking mode with chain-of-thought. Tiered pricing by context length.
Context 262K
Max output 32K
Pricing /1M tok $0.35 / $1.40 • API
Released Sep 23, 2025
Qwen
Qwen3 235B-A22B
active open-weight
Open-weight MoE Qwen3. 235B total, 22B active params. 128K context.
Context 128K
Max output 8K
Pricing /1M tok $0.15 / $0.60 • OpenRouter
Released Apr 28, 2025
Qwen
Qwen3 32B
active open-weight
Open-weight dense Qwen3. 32B params, 128K context.
Context 128K
Max output 8K
Pricing /1M tok $0.08 / $0.22 • OpenRouter
Released Apr 28, 2025
Qwen
QwQ 32B
active reasoning
Open-weight reasoning model. 32B params, chain-of-thought. Budget reasoning option.
Context 128K
Max output 16K
Pricing /1M tok $0.08 / $0.22 • OpenRouter
Released Mar 5, 2025
Qwen
Qwen2.5 VL 72B
active open-weight
Open-weight multimodal model. 72B params, 128K context, strong vision capabilities.
Context 128K
Max output 8K
Pricing /1M tok $0.15 / $0.40 • OpenRouter
Released Jan 28, 2025
Qwen
Qwen2.5 Coder 32B
active coding
Open-weight coding specialist. 32B params, 128K context.
Context 128K
Max output 8K
Pricing /1M tok $0.08 / $0.22 • OpenRouter
Released Nov 1, 2024
Qwen
Qwen2.5 72B
legacy open-weight
Previous-gen open-weight model. 72B dense. Superseded by Qwen3.
Context 128K
Max output 8K
Pricing /1M tok $0.15 / $0.40 • OpenRouter
Released Sep 19, 2024
Lifecycle
→ qwen3-235b
// lineage_chains
Model lineage
Predecessor → successor chains tracked for Qwen models.
Qwen2.5 72B legacy Sep 19, 2024
→
Qwen3 235B-A22B active Apr 28, 2025
// release_timeline
Qwen timeline
Qwen3.5 Flash released
Qwen3.5 speed model. 1M context, lowest cost in Qwen lineup.
Qwen3.5 Plus released
Qwen3.5 series balanced model. Text/image/video input. 1M context, faster and cheaper than Qwen3-Max.
Qwen3 Max released
Alibaba's flagship Qwen model. 262K context. Supports thinking mode with chain-of-thought. Tiered pricing by context length.
Qwen3 235B-A22B released
Open-weight MoE Qwen3. 235B total, 22B active params. 128K context.
Qwen3 32B released
Open-weight dense Qwen3. 32B params, 128K context.
QwQ 32B released
Open-weight reasoning model. 32B params, chain-of-thought. Budget reasoning option.
Qwen2.5 VL 72B released
Open-weight multimodal model. 72B params, 128K context, strong vision capabilities.
Qwen2.5 Coder 32B released
Open-weight coding specialist. 32B params, 128K context.
Qwen2.5 72B released
Previous-gen open-weight model. 72B dense. Superseded by Qwen3.