Qwen: Qwen3.5 397B A17B
Analysis Summary
Qwen: Qwen3.5 397B A17B sits in the Professional tier on our leaderboard, ranked #54 of 556 published models on overall intelligence. At $0.390 input and $2.34 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, vision, and reasoning.
Editorial notes
Qwen3.5 397B A17B delivers strong reasoning and vision support at under $0.40 per million input tokens, with a 262K context and solid agentic performance for the price.
Assessed May 14, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3.5 397B A17B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3.5-397b-a17b
|
| Provider | qwen |
| Release Date | February 16, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 65,536 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.39 | $0.000390 |
| Output | $2.34 | $0.002340 |
Live Performance
Live endpoint metrics ā refreshed every 30 minutes.
