Everything about Qwen3.5 397B-A17B

What you need to know

Released on February 15, 2026, Qwen3.5 397B-A17B is one of the 12 Alibaba Cloud (Qwen) models tracked on this site. It is an open-weight model: you can host it yourself on infrastructure you control, and 35 API providers listed on models.dev also offer it. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. That makes it 8 months old as of October 22, 2026.

We file it under open-weight models (68 models in this category on the site).

What it costs

Qwen3.5 397B-A17B costs $0.55 per million input tokens and $3.6 per million output tokens (median of 35 providers, checked on October 22, 2026).

In practice, an agent task that reads 20,000 tokens and writes 2,000 costs about $0.018, or $18.2 for 1,000 such tasks.

That is 3.6 times the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

What do independent benchmarks say?

According to results published by Epoch AI (checked on October 22, 2026), Qwen3.5 397B-A17B has a capability index of 59.2 out of 100, computed on 4 benchmarks from our basket.

It is not among the top 30 of the weekly ranking.

• GPQA Diamond (PhD-level science questions): 86.4% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 88.9% — the best tracked model, GPT-5.5 Pro, reaches 100%
• FrontierMath (very hard research-level mathematics): 31.2% — the best tracked model, GPT-6 Astra, reaches 93.7%
• APEX-Agents (professional tasks carried out by an agent): 24.9% — the best tracked model, Gemini 4 Argon, reaches 82.4%

Context and capabilities

Its context window reaches 262,144 tokens, roughly 393 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 8,192 tokens.

It accepts as input: text. Its knowledge stops at July 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (Qwen/Qwen3.5-397B-A17B). See also our list of open-source models.

Who is it for?

Given its category, Qwen3.5 397B-A17B is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Comparable models

In the same category, the models closest to Qwen3.5 397B-A17B are:

• DeepSeek V3.2 (DeepSeek, index 59.8)
• MiniMax-M3 (MiniMax, index 55.5)
• Qwen3.6 35B-A3B (Alibaba Cloud (Qwen), index 55.3)
• Kimi K2.7 Code (Moonshot AI, index 66.7)