Alibaba models in Big-AGI
Qwen3.8 Max and the rest of Model Studio at Alibaba's own rates - filtered to just the chat models, with resold models labeled "(Alibaba)".
All supported Alibaba models
ModelContextInputOutputReleased
DeepSeek V4.1 Flash 1017 (Alibaba)NEWHOTDeepSeek V4.1 Flash 1017 snapshot served via Alibaba Model Studio. Stronger agentic coding with shorter outputs. Multimodal 552B MoE with 1M context, native im…1M$0.30$1.20Oct 2026GLM-5.3 Prime (Alibaba)NEWZhipu GLM-5.3 on Alibaba's fast-serving tier (Prime): same model, 1.5-2x output speed, 2x price. 1M context, always-on thinking.1M$2.80$8.80Sep 2026DeepSeek V4.1 Flash (Alibaba)HOTDeepSeek V4.1 Flash served via Alibaba Model Studio. Multimodal 552B MoE with 1M context, native image input, and thinking on by default.1M$0.30$1.20Sep 2026Qwen3.8 Max 0902Upgraded 0902 snapshot of Qwen3.8 Max: stronger engineering-scale coding, agent tool orchestration, and visual understanding. 1M context, thinking, vision/vide…1M$2.00$6.00Sep 2026Qwen3.8 FlashLatest fast multimodal model of the Qwen3.8 line: 1M context, thinking (on by default), vision/video, 128K output.1M$0.15$0.47Aug 2026GLM-5.3 (Alibaba)Zhipu GLM-5.3 served via Alibaba Model Studio. 1M context, always-on thinking.1M$1.40$4.40Aug 2026Qwen3.8 27BOpen-weights 27B dense vision-language model of the Qwen3.8 line. 1M context, thinking, image/video input.1M$0.50$3.00Aug 2026DeepSeek V4 Pro (Alibaba)HOTDeepSeek V4 Pro served via Alibaba Model Studio (Alibaba pricing, well above DeepSeek-direct). 1M context, thinking.1M$2.40$4.80Aug 2026Qwen3.8 2.4T-A95BOpen-weights release of the Qwen3.8 flagship: 2.4T sparse MoE, ~95B active. Text-only serving with 1M context and always-on thinking.1M$2.00$6.00Aug 2026DeepSeek V4 Flash (Alibaba)HOTDeepSeek V4 Flash served via Alibaba Model Studio. 1M context, thinking.1M$0.20$0.40Jul 2026Qwen3.8 MaxFlagship 2.4T-parameter sparse MoE multimodal model with 1M context, thinking, and vision/video understanding.1M$2.00$6.00Jul 2026Kimi K3 (Alibaba)Moonshot Kimi K3 flagship served via Alibaba Model Studio. Multimodal, thinking on by default, 1M context.1M$3.00$15.00Jul 2026Qwen3.7 FlashLatest fast multimodal model with 1M context, thinking (on by default), vision, and 128K output.1M$0.03$0.13Jul 2026GLM-5.2 (Alibaba)Zhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking.1M$1.40$4.40Jun 2026Kimi K2.7 Code (Alibaba)Moonshot Kimi K2.7 Code served via Alibaba Model Studio. Multimodal, always-on thinking, 256K context.262K$0.95$4.00Jun 2026Qwen3.7 PlusMultimodal agent model with 1M context, native thinking, and vision/video understanding. Lower cost than Max.1M$0.40$1.60Jun 2026Qwen3.7 MaxFlagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.1M$2.50$7.50May 2026Qwen3.6 27BOpen 27B dense multimodal with thinking. 256K context.262K$0.60$3.60Apr 2026Qwen3.6 35B-A3BOpen 35B-A3B MoE multimodal with thinking. 256K context.262K$0.38$2.25Apr 2026Qwen3.6 FlashFast, cost-effective multimodal model with 1M context, near-flagship quality, vision/video, and built-in tools.1M$0.25$1.50Apr 2026Qwen3.6 Max PreviewdeprecatedQwen3.6 Max preview (never GA; superseded by Qwen3.7 Max). 256K context, thinking, text-only.262K$1.30$7.80Apr 2026GLM-5.1 (Alibaba)Zhipu GLM-5.1 served via Alibaba Model Studio, superseded by GLM-5.2. 200K context, thinking.203K$1.40$4.40Apr 2026Qwen3.6 PlusPrevious Plus tier, superseded by Qwen3.7 Plus. 1M context, thinking, vision.1M$0.50$3.00Apr 2026Qwen3.5 122B-A10BOpen 122B-A10B MoE multimodal with thinking. 256K context.262K$0.40$3.20Feb 2026Qwen3.5 27BOpen 27B dense multimodal with thinking. 256K context.262K$0.30$2.40Feb 2026Qwen3.5 35B-A3BOpen 35B-A3B MoE multimodal with thinking. 256K context.262K$0.25$2.00Feb 2026Qwen3.5 FlashFormer Flash tier, superseded by Qwen3.6/3.7 Flash. 1M context, thinking, vision.1M$0.10$0.40Feb 2026Qwen3.5 397B-A17BOpen 397B-A17B MoE multimodal with thinking. 256K context.262K$0.60$3.60Feb 2026Qwen3.5 PlusFormer Plus tier, superseded by Qwen3.6/3.7 Plus. 1M context, thinking, vision.1M$0.40$2.40Feb 2026Qwen3 Coder NextdeprecatedBudget agentic coder on the Qwen3-Next architecture. 256K context, non-thinking, tiered pricing.262K$0.30$1.50Feb 2026DeepSeek V3.2 (Alibaba)deprecatedDeepSeek V3.2 served via Alibaba Model Studio (superseded by V4). Thinking.131K$0.57$1.71Dec 2025Qwen3 VL FlashdeprecatedBudget VL tier below Qwen3 VL Plus. 256K context, thinking, vision.262K$0.05$0.40Oct 2025Qwen3 Coder PlusdeprecatedAgentic coding model with very long context. Tiered pricing by input length (up to 1M).1M$1.00$5.00Sep 2025Qwen3 MaxdeprecatedRetired 2025 flagship, superseded by Qwen3.6+ Max. 256K context; the base id now serves the thinking-capable 2026-01-23 snapshot.262K$1.20$6.00Sep 2025Qwen3 Vl 235b A22b InstructdeprecatedAlibaba model (not yet curated).131K--Sep 2025Qwen3 Vl 235b A22b ThinkingdeprecatedAlibaba model (not yet curated).131K--Sep 2025Qwen3 Next 80b A3b InstructdeprecatedAlibaba model (not yet curated).131K--Sep 2025Qwen3 Next 80b A3b ThinkingdeprecatedAlibaba model (not yet curated).131K--Sep 2025Qwen3 30b A3b Thinking 2507deprecatedAlibaba model (not yet curated).131K--Aug 2025Qwen3 30b A3b Instruct 2507deprecatedAlibaba model (not yet curated).131K--Jul 2025Qwen3 Coder FlashFormer budget coder, superseded by Qwen3.7 Plus. 1M context, non-thinking.1M$0.30$1.50Jul 2025Qwen3 235b A22b Thinking 2507deprecatedAlibaba model (not yet curated).131K--Jul 2025Qwen3 14bdeprecatedAlibaba model (not yet curated).131K--Apr 2025Qwen3 235b A22bdeprecatedAlibaba model (not yet curated).131K--Apr 2025Qwen3 30b A3bdeprecatedAlibaba model (not yet curated).131K--Apr 2025Qwen3 32bdeprecatedAlibaba model (not yet curated).131K--Apr 2025Qwen3 8bdeprecatedAlibaba model (not yet curated).131K--Apr 2025GLM-5.2 Fast (Alibaba)Zhipu GLM-5.2 fast-serving tier via Alibaba Model Studio (preview). Same model, lower latency, ~2x price.1M$2.80$8.80-Qvq MaxdeprecatedAlibaba model (not yet curated).131K---Qwen Coder PlusdeprecatedAlibaba model (not yet curated).131K---Qwen FlashFast and very low cost with hybrid thinking. 1M context.1M$0.05$0.40-Qwen MaxBest quality of the stable commercial line. 32K context.33K$1.60$6.40-Qwen PlusBalanced quality, speed, and cost with hybrid thinking. 1M context.1M$0.40$1.20-Qwen PlusBalanced quality, speed, and cost with hybrid thinking. 1M context.1M$0.40$1.20-Qwen TurbodeprecatedFastest and cheapest for simple tasks. 1M context.1M$0.05$0.20-Qwen Vl MaxdeprecatedAlibaba model (not yet curated).131K---Qwen Vl PlusdeprecatedAlibaba model (not yet curated).131K---Qwen3 235b A22b Instruct 2507deprecatedAlibaba model (not yet curated).131K---Qwen3.7 MaxFlagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.1M$2.50$7.50-Qwen3 Coder 480b A35b InstructdeprecatedAlibaba model (not yet curated).131K---Qwen3 MaxdeprecatedRetired 2025 flagship, superseded by Qwen3.6+ Max. 256K context; the base id now serves the thinking-capable 2026-01-23 snapshot.262K$1.20$6.00-Qwen3 VL PlusCurrent vision-language model with strong visual reasoning and thinking. Tiered pricing by input length (up to 256K).262K$0.20$1.60-Qwq PlusdeprecatedAlibaba model (not yet curated).131K---63 models · sorted by release date · prices in USD per 1M tokens · refreshed hourlyCompare every model across vendors ->
Get started in 3 steps
1
Create an API key at the Alibaba console.
2
Paste it into Big-AGI's model settings.
3
Start chatting, or Beam it against other models and fuse the answers.
Running Alibaba in Big-AGI
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 no intermediary: billing runs directly between you and Alibaba Cloud, and your keys stay in your browser.
- Your key, your billing. Usage is billed by Alibaba Cloud to your account. Big-AGI does not meter or charge for model usage.
- Chat models only. Alibaba's raw catalog mixes Qwen chat models in with OCR, speech, translation, and call-center products. Big-AGI filters those out so only genuine chat models show up, which Alibaba's own console does not do for you.
- Third-party models, labeled honestly. Model Studio also hosts other labs' models at Alibaba's own pricing. Big-AGI tags them "(Alibaba)" so you never mistake a hosted copy for the vendor-direct version.
Why not just the Qwen app?
Alibaba's own Qwen app is free and covers general chat well, but it cannot put Qwen's answer next to GPT's, Claude's, or Gemini's on the same prompt. Beam can: agreement across labs is a stronger signal than any single model's confidence, and disagreement tells you where to dig further. You also get parameters the app hides (temperature, system prompt, per-turn model swaps), and a key that stays in your browser instead of sitting on Alibaba's servers.
Your keys and your data
Turn on Direct Connection and the browser calls Alibaba directly, bypassing the Big-AGI server, whenever your key is client-side and Alibaba allows it. Your keys stay in your browser. Chats are stored locally first and sync only if you turn it on. The AI Inspector opens on any message to show the exact request sent to Alibaba, the token counts, and a cost estimate for that call.
Qwen in Beam
Run Qwen in parallel with Claude, GPT, and Gemini on the same prompt, then reach for Fusions: several strategies that combine, cross-check, and synthesize the parallel answers, which beats just picking the single best one. Parallel runs use more tokens than a single chat.
Bring your Alibaba key. Keep control.
Your key, your data, your choice of model. Big-AGI's Open branch is open source and self-hostable, so you can check exactly how Alibaba is called.
Launch Big-AGIBIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego