Bring your own Alibaba key and use Alibaba at its own API rates, with no markup. Keys and chats stay in your browser. Run Alibaba in parallel with other models, then compare and merge the answers.
Kimi K2.7 Code (Alibaba)
NEWMoonshot Kimi K2.7 Code served via Alibaba Model Studio. Multimodal, always-on thinking, 256K context. (Alibaba pricing not yet published.)
262K
-
-
Jun 2026
GLM-5.2 (Alibaba)
NEWZhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking. (Alibaba pricing not yet published.)
1M
-
-
Jun 2026
DeepSeek V4 Pro (Alibaba)
NEWDeepSeek V4 Pro served via Alibaba Model Studio (Alibaba pricing, ~5x DeepSeek-direct). 1M context, thinking.
1M
$2.4
$4.8
Jun 2026
DeepSeek V3.2 (Alibaba)
NEWDeepSeek V3.2 served via Alibaba Model Studio (superseded by V4). Thinking.
131K
$0.57
$1.71
Jun 2026
DeepSeek V4 Flash (Alibaba)
NEWDeepSeek V4 Flash served via Alibaba Model Studio. 1M context, thinking.
1M
$0.2
$0.4
Jun 2026
[?] Qwen3.7 Max [2026 05 17]
NEWFlagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.
1M
$2.5
$7.5
Jun 2026
Qwen3.6 Flash
NEWFast, cost-effective multimodal model with 1M context, near-flagship quality, vision/video, and built-in tools.
1M
$0.25
$1.5
Jun 2026
[?] Qwen3.7 Max [preview]
NEWFlagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.
1M
$2.5
$7.5
Jun 2026
Qwen3.7 Plus
NEWMultimodal agent model with 1M context, native thinking, and vision/video understanding. Lower cost than Max.
1M
$0.4
$1.6
Jun 2026
Qwen3 Coder Plus
Agentic coding model with very long context. Tiered pricing by input length (up to 1M).
1M
$1
$5
May 2026
[?] Qwen3 VL Plus [2025 12 19]
Current vision-language model with strong visual reasoning and thinking. Tiered pricing by input length (up to 256K).
262K
$0.2
$1.6
Apr 2026
Glm 5.1
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Next 80b A3b Instruct
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 235b A22b Instruct 2507
Alibaba model (not yet curated).
131K
-
-
-
Qwen Plus
Balanced quality, speed, and cost with hybrid thinking. 1M context.
1M
$0.4
$1.2
-
Qwen3 Next 80b A3b Thinking
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 30b A3b Thinking 2507
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 8b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 235b A22b Thinking 2507
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.6 35b A3b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 32b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 30b A3b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Vl 235b A22b Instruct
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Coder Next
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 235b A22b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 30b A3b Instruct 2507
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 14b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.5 122b A10b
Alibaba model (not yet curated).
131K
-
-
-
Qwen Max
Best quality of the stable commercial line. 32K context.
33K
$1.6
$6.4
-
Qwen3.5 Flash 2026 02 23
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.5 35b A3b
Alibaba model (not yet curated).
131K
-
-
-
Qwen Vl Max
Alibaba model (not yet curated).
131K
-
-
-
Qwq Plus 2025 03 05
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Vl Flash 2025 10 15
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.5 27b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Coder Flash
Alibaba model (not yet curated).
131K
-
-
-
Qwen Vl Plus
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.5 397b A17b
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.6 Max Preview
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Max Preview
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.5 Plus 2026 02 15
Alibaba model (not yet curated).
131K
-
-
-
Qwen Coder Plus
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.6 Plus
Alibaba model (not yet curated).
131K
-
-
-
Qwen Flash
Fast and very low cost with hybrid thinking. 1M context.
1M
$0.05
$0.4
-
Qwen3 Max
Alibaba model (not yet curated).
131K
-
-
-
Qwen3.6 27b
Alibaba model (not yet curated).
131K
-
-
-
Qvq Max
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Vl 235b A22b Thinking
Alibaba model (not yet curated).
131K
-
-
-
Qwen3 Coder 480b A35b Instruct
Alibaba model (not yet curated).
131K
-
-
-
Qwen Turbo
Fastest and cheapest for simple tasks. 1M context.
1M
$0.05
$0.2
-
[?] Qwen Plus [latest]
Balanced quality, speed, and cost with hybrid thinking. 1M context.
1M
$0.4
$1.2
-
Kimi K2.7 Code (Alibaba)
NEWMoonshot Kimi K2.7 Code served via Alibaba Model Studio. Multimodal, always-on thinking, 256K context. (Alibaba pricing not yet published.)
GLM-5.2 (Alibaba)
NEWZhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking. (Alibaba pricing not yet published.)
DeepSeek V4 Pro (Alibaba)
NEWDeepSeek V4 Pro served via Alibaba Model Studio (Alibaba pricing, ~5x DeepSeek-direct). 1M context, thinking.
DeepSeek V3.2 (Alibaba)
NEWDeepSeek V3.2 served via Alibaba Model Studio (superseded by V4). Thinking.
DeepSeek V4 Flash (Alibaba)
NEWDeepSeek V4 Flash served via Alibaba Model Studio. 1M context, thinking.
[?] Qwen3.7 Max [2026 05 17]
NEWFlagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.
Qwen3.6 Flash
NEWFast, cost-effective multimodal model with 1M context, near-flagship quality, vision/video, and built-in tools.
[?] Qwen3.7 Max [preview]
NEWFlagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.
Qwen3.7 Plus
NEWMultimodal agent model with 1M context, native thinking, and vision/video understanding. Lower cost than Max.
Qwen3 Coder Plus
Agentic coding model with very long context. Tiered pricing by input length (up to 1M).
[?] Qwen3 VL Plus [2025 12 19]
Current vision-language model with strong visual reasoning and thinking. Tiered pricing by input length (up to 256K).
Glm 5.1
Alibaba model (not yet curated).
Qwen3 Next 80b A3b Instruct
Alibaba model (not yet curated).
Qwen3 235b A22b Instruct 2507
Alibaba model (not yet curated).
Qwen Plus
Balanced quality, speed, and cost with hybrid thinking. 1M context.
Qwen3 Next 80b A3b Thinking
Alibaba model (not yet curated).
Qwen3 30b A3b Thinking 2507
Alibaba model (not yet curated).
Qwen3 8b
Alibaba model (not yet curated).
Qwen3 235b A22b Thinking 2507
Alibaba model (not yet curated).
Qwen3.6 35b A3b
Alibaba model (not yet curated).
Qwen3 32b
Alibaba model (not yet curated).
Qwen3 30b A3b
Alibaba model (not yet curated).
Qwen3 Vl 235b A22b Instruct
Alibaba model (not yet curated).
Qwen3 Coder Next
Alibaba model (not yet curated).
Qwen3 235b A22b
Alibaba model (not yet curated).
Qwen3 30b A3b Instruct 2507
Alibaba model (not yet curated).
Qwen3 14b
Alibaba model (not yet curated).
Qwen3.5 122b A10b
Alibaba model (not yet curated).
Qwen Max
Best quality of the stable commercial line. 32K context.
Qwen3.5 Flash 2026 02 23
Alibaba model (not yet curated).
Qwen3.5 35b A3b
Alibaba model (not yet curated).
Qwen Vl Max
Alibaba model (not yet curated).
Qwq Plus 2025 03 05
Alibaba model (not yet curated).
Qwen3 Vl Flash 2025 10 15
Alibaba model (not yet curated).
Qwen3.5 27b
Alibaba model (not yet curated).
Qwen3 Coder Flash
Alibaba model (not yet curated).
Qwen Vl Plus
Alibaba model (not yet curated).
Qwen3.5 397b A17b
Alibaba model (not yet curated).
Qwen3.6 Max Preview
Alibaba model (not yet curated).
Qwen3 Max Preview
Alibaba model (not yet curated).
Qwen3.5 Plus 2026 02 15
Alibaba model (not yet curated).
Qwen Coder Plus
Alibaba model (not yet curated).
Qwen3.6 Plus
Alibaba model (not yet curated).
Qwen Flash
Fast and very low cost with hybrid thinking. 1M context.
Qwen3 Max
Alibaba model (not yet curated).
Qwen3.6 27b
Alibaba model (not yet curated).
Qvq Max
Alibaba model (not yet curated).
Qwen3 Vl 235b A22b Thinking
Alibaba model (not yet curated).
Qwen3 Coder 480b A35b Instruct
Alibaba model (not yet curated).
Qwen Turbo
Fastest and cheapest for simple tasks. 1M context.
[?] Qwen Plus [latest]
Balanced quality, speed, and cost with hybrid thinking. 1M context.
Add your Alibaba Cloud Model Studio API key and run the Qwen family, plus the other models Alibaba serves, at Alibaba's own API rates. Big-AGI adds no markup and keeps your keys and chats in your browser, not on its servers.
Your key, your data, your choice of model. Big-AGI is open source and self-hostable, so you can check exactly how Alibaba is called.
BIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego