Start building
MODEL COLLECTIONALIBABA · LANGUAGE MODEL FAMILY

Qwen API

Use Alibaba Qwen through SandBase: Qwen3.8 Max and its open-weight 2.4T release, compact 27B models, Omni Flash for audio and video input, and Qwen3.7 tiers.

Explore the lineupGet API key

Explore the model lineup

Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.

Qwen3.8 Max output preview
llm
Alibaba

Qwen3.8 Max

Qwen3.8 Max is Alibaba's flagship Qwen3.8 model, a 2.4-trillion-parameter Mixture-of-Experts reasoning model with native vision understanding, released in August 2026. Alibaba positions it for long-ho...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $2
MODE1M context
View model
Qwen3.8 27B output preview
llm
Alibaba

Qwen3.8 27B

Qwen3.8 27B is the compact dense member of Alibaba's Qwen3.8 family, an open-weight native vision-language model that understands images and video, with thinking mode on by default. Compared with Qwen...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $0.5
MODE1M context
View model
Qwen3.7 Flash output preview
llm
Alibaba

Qwen3.7 Flash

Qwen3.7 Flash is the Flash tier of Alibaba's Qwen3.7 series, a native vision-language reasoning model that accepts text, images and video, released in July 2026. Alibaba describes it as an upgrade ove...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $0.03
MODE1M context
View model
Qwen3.8 Max (0902) output preview
llm
Alibaba

Qwen3.8 Max (0902)

Qwen3.8 Max (0902) is the pinned snapshot of Alibaba's Qwen3.8 Max dated September 2, 2026, intended for workloads that need a fixed version. Alibaba describes it as an upgraded snapshot with stronger...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $2
MODE1M context
View model
Qwen3.7 Plus output preview
llm
Alibaba

Qwen3.7 Plus

Qwen3.7 Plus is the balanced Plus tier of Alibaba's Qwen3.7 series, a reasoning model with text and image input released in June 2026. Alibaba highlights its multimodal hybrid agent abilities: perceiv...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $0.4
MODE1M context
View model
llm
Alibaba

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is the open-weight release of Alibaba's Qwen3.8 Max-class model, a sparse Mixture-of-Experts with 2.4 trillion total and about 95 billion active parameters, published in August 2026 ...

  • chat
  • reasoning
  • structured_output
  • function_calling
PRICEFrom $2
MODE1M context
View model
Qwen3.8 Omni Flash output preview
llm
Alibaba

Qwen3.8 Omni Flash

Qwen3.8 Omni Flash is Alibaba's omni-modal reasoning model in the Qwen3.8 family, accepting text, image, audio and video input and returning text, with a 1M-token context window. Alibaba positions it ...

  • chat
  • vision
  • audio_input
  • reasoning
PRICEFrom $0.15
MODE1M context
View model
Qwen3.8 Max Prime output preview
llm
Alibaba

Qwen3.8 Max Prime

Qwen3.8 Max Prime is the Fast mode (Prime) serving option for Alibaba's Qwen3.8 Max: the same model with the same vision input and reasoning, delivered at higher output speed. Alibaba states Fast mode...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $4
MODE1M context
View model
Qwen3.6 Plus output preview
llm
Alibaba

Qwen3.6 Plus

Qwen3.6 Plus is the Plus tier of Alibaba's Qwen3.6 series, a hosted native vision-language reasoning model released in April 2026. Alibaba reports marked gains over the Qwen3.5 series in agentic codin...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $0.5
MODE1M context
View model
Qwen3.6 27B output preview
llm
Alibaba

Qwen3.6 27B

Qwen3.6 27B is an open-weight dense 27-billion-parameter vision-language model in Alibaba's Qwen3.6 family, released in April 2026 with thinking and non-thinking modes. Qwen positions it for agentic c...

  • chat
  • vision
  • reasoning
  • structured_output
PRICEFrom $0.6
MODE262K context
View model
Qwen3.7 Max output preview
llm
Alibaba

Qwen3.7 Max

Qwen3.7 Max is the largest and most capable model in Alibaba's Qwen3.7 series as of its May 2026 release, a reasoning model built for agent-centric work and offered here with text input and output. Al...

  • chat
  • reasoning
  • structured_output
  • function_calling
PRICEFrom $2.5
MODE1M context
View model

Model lineup

Context window and positioning from each provider.

ModelContextPositioning
Qwen3.8 Max1000KQwen3.8 Max is Alibaba's flagship Qwen3.8 model, a 2.4-trillion-parameter Mixture-of-Experts reasoning model with native vision understanding,…
Qwen3.8 Max (0902)1000KQwen3.8 Max (0902) is the pinned snapshot of Alibaba's Qwen3.8 Max dated September 2, 2026, intended for workloads that need a fixed version
Qwen3.8 Max Prime1000KQwen3.8 Max Prime is the Fast mode (Prime) serving option for Alibaba's Qwen3.8 Max: the same model with the same vision input and reasoning,…
Qwen3.7 Plus1000KQwen3.7 Plus is the balanced Plus tier of Alibaba's Qwen3.7 series, a reasoning model with text and image input released in June 2026
Qwen3.7 Flash1000KQwen3.7 Flash is the Flash tier of Alibaba's Qwen3.7 series, a native vision-language reasoning model that accepts text, images and video, released…
Qwen3.7 Max1000KQwen3.7 Max is the largest and most capable model in Alibaba's Qwen3.7 series as of its May 2026 release, a reasoning model built for agent-centric…
Qwen3.6 Plus1000KQwen3.6 Plus is the Plus tier of Alibaba's Qwen3.6 series, a hosted native vision-language reasoning model released in April 2026
Qwen3.6 27B262KQwen3.6 27B is an open-weight dense 27-billion-parameter vision-language model in Alibaba's Qwen3.6 family, released in April 2026 with thinking and…
Qwen3.8 2.4T A95B1000KQwen3.8 2.4T A95B is the open-weight release of Alibaba's Qwen3.8 Max-class model, a sparse Mixture-of-Experts with 2.4 trillion total and about 95…
Qwen3.8 27B1000KQwen3.8 27B is the compact dense member of Alibaba's Qwen3.8 family, an open-weight native vision-language model that understands images and video,…
Qwen3.8 Omni Flash1000KQwen3.8 Omni Flash is Alibaba's omni-modal reasoning model in the Qwen3.8 family, accepting text, image, audio and video input and returning text,…

Current Qwen models

SandBase serves Qwen on the OpenAI-compatible POST /v1/chat/completions. Current Qwen models are native vision-language reasoning models with up to 1M tokens of context.

  • Qwen3.8 Max: Alibaba's flagship 2.4-trillion-parameter MoE reasoning model. Max Prime is the same model in a faster serving mode, and 0902 is a pinned snapshot.
  • Qwen3.8 2.4T A95B: the open-weight release of the Max-class model.
  • Qwen3.8 27B and Qwen3.6 27B: compact open-weight dense models.
  • Qwen3.8 Omni Flash: accepts text, image, audio and video input.
  • Qwen3.7 Max, Plus and Flash; Qwen3.6 Plus: earlier tiers.

For Alibaba image and video, see Qwen Image and Wan. Compare with other Chinese models on Chinese LLM APIs.

Start using Qwen API on SandBase

Switch models by changing one field.

  1. 01

    Create an API key

    Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.

    TERMINAL

    export SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY"
  2. 02

    Send a chat request

    Call the OpenAI-compatible Chat Completions API with model alibaba/qwen3.8-max. Any OpenAI SDK works with base URL https://api.sandbase.ai/v1.

    TERMINAL

    curl https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "alibaba/qwen3.8-max", "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}'
  3. 03

    Connect your AI tools

    Use the same key in Claude Code, Codex, Cursor and other clients. See Use in AI tools for setup.

Questions, answered

Which Qwen models are open-weight?

Qwen3.8 2.4T A95B, Qwen3.8 27B and Qwen3.6 27B are described as open-weight.

What is Qwen3.8 Max Prime?

The same Qwen3.8 Max model with the same inputs, served in a faster mode at a higher price.

Which Qwen accepts audio and video?

Qwen3.8 Omni Flash accepts text, image, audio and video input.

What is the cheapest Qwen?

Qwen3.7 Flash is the lowest-priced current Qwen tier.

READY / SET / RUN

Build with Qwen API.

One key, consistent APIs, and usage-based pricing across every model on this page.

Get your API keyRead the docs