Qwen 3.5 397B
Alibaba's flagship open-weight multimodal model with 397B parameters, native vision, and efficient MoE architecture — now on Venice.
Get API keyWhat is Qwen 3.5 397B?
Qwen 3.5 397B is Alibaba's flagship open-weight multimodal AI, released in February 2026. Built on a sparse Mixture-of-Experts architecture with 397 billion total parameters and 17 billion active per token, it supports vision, reasoning, tool use, and code generation, delivering high efficiency and broad language coverage across 201 languages.
Use Qwen 3.5 397B privately on Venice
On Venice, Qwen 3.5 397B runs with anonymized privacy — your prompts are never stored or profiled. You get full access to its multimodal and agentic capabilities, including vision and web search, without sacrificing sovereignty. The model is uncensored in operation, enabling permissionless use for developers and enterprises.
What can Qwen 3.5 397B do?
- •Native multimodal support — unified vision-language processing via early fusion training, enabling image and video input.
- •Efficient inference — sparse MoE architecture activates only 17B of 397B parameters per token, balancing performance and cost.
- •Strong agentic and reasoning capabilities, with official support for tool calling, web search, and structured JSON output.
- •Extensive language coverage — supports 201 languages, making it one of the most globally accessible open models.
- •Open weights and commercially permissive license (Apache 2.0) enable self-hosting, fine-tuning, and enterprise integration.
- •Not the most cost-efficient option — higher output cost compared to rivals like DeepSeek V4 Flash.
- •Closed reasoning mode in some deployments; the full 'thinking' capability may require specific configuration.
- •While open weights, the training data and full pipeline are not fully transparent.
Qwen 3.5 397B capabilities
- Tool use / function calling
- Vision (image input)
- Reasoning
- Web search
- Code-optimized
- Structured output (JSON schema)
- Audio input
- Video input
- Multiple image inputs
- Log probabilities
How to use Qwen 3.5 397B via API
Venice exposes an OpenAI-compatible API. Swap your base URL and call qwen3-5-397b-a17b.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-5-397b-a17b",
"messages": [{ "role": "user", "content": "Explain quantum tunneling simply." }]
}'Specifications
Pricing
Billed per token on Venice: $0.75 per 1M input tokens and $4.50 per 1M output tokens.
New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.
Qwen 3.5 397B vs alternatives
| Model | Max output | Strongest at | Open weights | Price (Venice) |
|---|---|---|---|---|
| Qwen 3.5 397B | 32.768K tokens | Multimodal agents, code, reasoning | Yes | $0.75 in · $4.50 out / 1M |
| Claude Opus 5 | 32.768K tokens | Complex reasoning, enterprise tasks | No | $6 in · $30 out / 1M |
| DeepSeek V4 Flash 0731 | 32.768K tokens | Speed and cost efficiency | No | $0.17 in · $0.35 out / 1M |
| Google Gemma 4 31B Instruct | 32.768K tokens | Efficiency and open access | Yes | $0.12 in · $0.36 out / 1M |
Open, efficient MoE model with strong vision and agentic performance.
What is Qwen 3.5 397B good for?
- •Multimodal RAG applications combining text and image inputs.
- •Internationalized agents and chatbots requiring broad language support.
- •Code generation and reasoning workflows with tool integration.
- •Enterprise automation leveraging vision, web search, and function calling.
- •Privacy-sensitive deployments where prompt retention is prohibited.
Prompting tips
- •Use explicit image URLs or base64-encoded images to trigger vision mode.
- •Enable tool use by specifying available functions in JSON schema format.
- •For complex reasoning tasks, prompt with 'think step by step' to engage reasoning mode if available.
- •Leverage its multilingual strength by specifying non-English languages directly in the prompt.
Version history
Previous generation, text-only
CurrentCurrent — native vision, MoE, open weights
Frequently asked questions
Qwen 3.5 397B is Alibaba's flagship open-weight multimodal AI model, released in February 2026. It features a 397B-parameter sparse Mixture-of-Experts architecture with 17B active per token, supporting vision, reasoning, tool use, and code generation across 201 languages.
Yes. Qwen 3.5 397B is open weights under the Apache 2.0 license, allowing free commercial use, self-hosting, and fine-tuning. The model weights are publicly available on Hugging Face.
On Venice, it costs $0.75 per 1M input tokens and $4.50 per 1M output tokens. There are no upfront fees or subscriptions — billing is per token used.
Yes. It natively supports image and video input through unified vision-language training, making it one of the first open models to integrate multimodal understanding directly into its core architecture.
Yes. The model supports function calling and tool use, including structured JSON output and integration with external tools like web search and code execution environments.
Qwen 3.5 397B is open, multimodal, and far more cost-effective, while Claude Opus 5 excels in complex reasoning and enterprise readiness but is closed and significantly more expensive. Choose Qwen for open, vision-capable agents; Claude for closed-loop enterprise workflows.
The model has a 128K token context window on Venice, with research versions supporting up to 262K tokens via YaRN extension. The maximum output length is 32,768 tokens.
Related models
Run Qwen 3.5 397B privately.
No prompt logging. No data used for training. Free to start — no credit card.
