Big-AGI Logo
BIG-AGI

BEAM

Features

Rankings

Pro

Docs

GitHub

LAUNCH APP

Use Alibaba Models in Big-AGI.

Bring your own key: Alibaba's API rates, no markup. Keys and chats stay in your browser. Run Alibaba in parallel with other models, then compare and merge the answers.

GLM-5.2 (Alibaba)
Qwen3.7 Max
GLM-5.2 (Alibaba)
Launch Big-AGI

All supported Alibaba models

ModelContextInputOutputReleased

GLM-5.2 (Alibaba)

NEW
ReasoningTools / functions

Zhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking.

1M

$1.1

$3.85

Jun 2026

Qwen3.7 Max

NEW
ReasoningTools / functions

Flagship 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

GLM-5.2 (Alibaba)

NEW
ReasoningTools / functions

Zhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking.

1M

$1.1

$3.85

Jun 2026

Qwen3.7 Plus

VisionReasoningTools / functions

Multimodal agent model with 1M context, native thinking, and vision/video understanding. Lower cost than Max.

1M

$0.4

$1.6

Jun 2026

Kimi K2.7 Code (Alibaba)

VisionReasoningTools / functions

Moonshot Kimi K2.7 Code served via Alibaba Model Studio. Multimodal, always-on thinking, 256K context.

262K

$0.89

$3.71

Jun 2026

Qwen3.7 Max

ReasoningTools / functions

Flagship 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

May 2026

Qwen3 VL Plus

VisionReasoningTools / functions

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

Qwen3.6 Flash

VisionReasoningTools / functions

Fast, cost-effective multimodal model with 1M context, near-flagship quality, vision/video, and built-in tools.

1M

$0.25

$1.5

Apr 2026

Qwen3.6 Max Preview

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2026

Qwen3.5 Plus 2026 02 15

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2026

Qwen3.6 35b A3b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2026

Qwen3.6 27b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2026

DeepSeek V4 Pro (Alibaba)

ReasoningTools / functions

DeepSeek V4 Pro served via Alibaba Model Studio (Alibaba pricing, ~5x DeepSeek-direct). 1M context, thinking.

1M

$2.4

$4.8

Apr 2026

DeepSeek V4 Flash (Alibaba)

ReasoningTools / functions

DeepSeek V4 Flash served via Alibaba Model Studio. 1M context, thinking.

1M

$0.2

$0.4

Apr 2026

Glm 5.1

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2026

Qwen3.6 Plus

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2026

Qwen3.5 35b A3b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Feb 2026

Qwen3.5 27b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Feb 2026

Qwen3.5 122b A10b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Feb 2026

Qwen3.5 397b A17b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Feb 2026

Qwen3 Coder Next

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Feb 2026

DeepSeek V3.2 (Alibaba)

ReasoningTools / functions

DeepSeek V3.2 served via Alibaba Model Studio (superseded by V4). Thinking.

131K

$0.57

$1.71

Dec 2025

Qwen3 Max

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Sep 2025

Qwen3 Vl 235b A22b Thinking

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Sep 2025

Qwen3 Coder Plus

Tools / functions

Agentic coding model with very long context. Tiered pricing by input length (up to 1M).

1M

$1

$5

Sep 2025

Qwen3 Vl 235b A22b Instruct

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Sep 2025

Qwen3 Coder Flash

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Sep 2025

Qwen3 Next 80b A3b Instruct

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Sep 2025

Qwen3 Next 80b A3b Thinking

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Sep 2025

Qwen3 30b A3b Thinking 2507

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Aug 2025

Qwen3 30b A3b Instruct 2507

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Jul 2025

Qwen3 235b A22b Thinking 2507

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Jul 2025

Qwen3 32b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2025

Qwen3 14b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2025

Qwen3 30b A3b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2025

Qwen3 8b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2025

Qwen3 235b A22b

Tools / functions

Alibaba model (not yet curated).

131K

-

-

Apr 2025

Qwen Plus

ReasoningTools / functions

Balanced quality, speed, and cost with hybrid thinking. 1M context.

1M

$0.4

$1.2

Feb 2025

Qwen3 Vl Flash 2025 10 15

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen Turbo

Tools / functions

Fastest and cheapest for simple tasks. 1M context.

1M

$0.05

$0.2

-

Qwq Plus 2025 03 05

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen Flash

ReasoningTools / functions

Fast and very low cost with hybrid thinking. 1M context.

1M

$0.05

$0.4

-

Qwen Coder Plus

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen3 Max Preview

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen3.5 Flash 2026 02 23

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen Vl Plus

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen Vl Max

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen3 235b A22b Instruct 2507

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qvq Max

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen Max

Tools / functions

Best quality of the stable commercial line. 32K context.

33K

$1.6

$6.4

-

Qwen3 Coder 480b A35b Instruct

Tools / functions

Alibaba model (not yet curated).

131K

-

-

-

Qwen Plus

ReasoningTools / functions

Balanced quality, speed, and cost with hybrid thinking. 1M context.

1M

$0.4

$1.2

-

GLM-5.2 (Alibaba)

NEW
Jun 2026

Zhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking.

ReasoningTools / functions
1M · in $1.1 · out $3.85

Qwen3.7 Max

NEW
Jun 2026

Flagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.

ReasoningTools / functions
1M · in $2.5 · out $7.5

GLM-5.2 (Alibaba)

NEW
Jun 2026

Zhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking.

ReasoningTools / functions
1M · in $1.1 · out $3.85

Qwen3.7 Plus

Jun 2026

Multimodal agent model with 1M context, native thinking, and vision/video understanding. Lower cost than Max.

VisionReasoningTools / functions
1M · in $0.4 · out $1.6

Kimi K2.7 Code (Alibaba)

Jun 2026

Moonshot Kimi K2.7 Code served via Alibaba Model Studio. Multimodal, always-on thinking, 256K context.

VisionReasoningTools / functions
262K · in $0.89 · out $3.71

Qwen3.7 Max

May 2026

Flagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.

ReasoningTools / functions
1M · in $2.5 · out $7.5

Qwen3 VL Plus

Apr 2026

Current vision-language model with strong visual reasoning and thinking. Tiered pricing by input length (up to 256K).

VisionReasoningTools / functions
262K · in $0.2 · out $1.6

Qwen3.6 Flash

Apr 2026

Fast, cost-effective multimodal model with 1M context, near-flagship quality, vision/video, and built-in tools.

VisionReasoningTools / functions
1M · in $0.25 · out $1.5

Qwen3.6 Max Preview

Apr 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.5 Plus 2026 02 15

Apr 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.6 35b A3b

Apr 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.6 27b

Apr 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

DeepSeek V4 Pro (Alibaba)

Apr 2026

DeepSeek V4 Pro served via Alibaba Model Studio (Alibaba pricing, ~5x DeepSeek-direct). 1M context, thinking.

ReasoningTools / functions
1M · in $2.4 · out $4.8

DeepSeek V4 Flash (Alibaba)

Apr 2026

DeepSeek V4 Flash served via Alibaba Model Studio. 1M context, thinking.

ReasoningTools / functions
1M · in $0.2 · out $0.4

Glm 5.1

Apr 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.6 Plus

Apr 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.5 35b A3b

Feb 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.5 27b

Feb 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.5 122b A10b

Feb 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.5 397b A17b

Feb 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Coder Next

Feb 2026

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

DeepSeek V3.2 (Alibaba)

Dec 2025

DeepSeek V3.2 served via Alibaba Model Studio (superseded by V4). Thinking.

ReasoningTools / functions
131K · in $0.57 · out $1.71

Qwen3 Max

Sep 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Vl 235b A22b Thinking

Sep 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Coder Plus

Sep 2025

Agentic coding model with very long context. Tiered pricing by input length (up to 1M).

Tools / functions
1M · in $1 · out $5

Qwen3 Vl 235b A22b Instruct

Sep 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Coder Flash

Sep 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Next 80b A3b Instruct

Sep 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Next 80b A3b Thinking

Sep 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 30b A3b Thinking 2507

Aug 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 30b A3b Instruct 2507

Jul 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 235b A22b Thinking 2507

Jul 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 32b

Apr 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 14b

Apr 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 30b A3b

Apr 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 8b

Apr 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 235b A22b

Apr 2025

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Plus

Feb 2025

Balanced quality, speed, and cost with hybrid thinking. 1M context.

ReasoningTools / functions
1M · in $0.4 · out $1.2

Qwen3 Vl Flash 2025 10 15

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Turbo

-

Fastest and cheapest for simple tasks. 1M context.

Tools / functions
1M · in $0.05 · out $0.2

Qwq Plus 2025 03 05

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Flash

-

Fast and very low cost with hybrid thinking. 1M context.

ReasoningTools / functions
1M · in $0.05 · out $0.4

Qwen Coder Plus

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 Max Preview

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3.5 Flash 2026 02 23

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Vl Plus

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Vl Max

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen3 235b A22b Instruct 2507

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qvq Max

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Max

-

Best quality of the stable commercial line. 32K context.

Tools / functions
33K · in $1.6 · out $6.4

Qwen3 Coder 480b A35b Instruct

-

Alibaba model (not yet curated).

Tools / functions
131K · in - · out -

Qwen Plus

-

Balanced quality, speed, and cost with hybrid thinking. 1M context.

ReasoningTools / functions
1M · in $0.4 · out $1.2
52 models · sorted by release date · prices in USD per 1M tokens · refreshed every 30 minutesCompare 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 is open source and self-hostable, so you can check exactly how Alibaba is called.

Launch Big-AGI

<- All Models

Alibaba

Anthropic

AWS Bedrock

Azure

Cerebras

DeepSeek

Fireworks AI

Google Gemini

Groq

MiniMax

Mistral

Moonshot

OpenAI

OpenRouter

Perplexity

Sakana AI

SpaceXAI

Together AI

Z.ai

BIG-AGI

Product

FeaturesModelsControlsChangelogBEAM Technology

Resources

DocumentationDiscordGitHub

Company

Email UsPrivacyTerms

© 2026 Token Fabrics·Built with passion in San Diego