Qwen3.5 397B-A17B — Benchmark Scores, Pricing & Performance Analysis
Qwen3.5 397B-A17B is an AI model by Alibaba. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Artificial Analysis composite intelligence score across 10 sub-benchmarks
Artificial Analysis (via OpenRouter)Coding Benchmarks
Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Reasoning Benchmarks
Artificial Analysis composite score for multi-step tool-using tasks
Artificial Analysis (via OpenRouter)Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 30 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Nvidia | $0 | $0 | — | 262K | — |
| UnoRouter | $0 | $0 | — | 262K | — |
| Alibaba (China) | $0.172 | $1.032 | — | 262K | — |
| EmpirioLabs AI | $0.172 | $1.032 | $0.172 | 256K | — |
| Merge Gateway | $0.172 | $1.032 | $0.0344 | 256K | — |
| OrcaRouter | $0.172 | $1.032 | — | 262K | — |
| Vultr | $0.3 | $2 | — | 262K | — |
| CrofAI | $0.35 | $1.75 | $0.07 | 262K | — |
| Kilo Gateway | $0.39 | $2.34 | — | 262K | — |
| SiliconFlow | $0.39 | $2.34 | — | 262K | — |
| TokenGo | $0.4 | $2.65 | $0.2 | 262K | — |
| Ofox | $0.55 | $3.5 | $0.55 | 256K | — |
| OpenRouter | $0.55 | $3.5 | $0.225 | 262K | Supported |
| Alibaba | $0.6 | $3.6 | — | 262K | Supported |
| Cloudflare AI Gateway | $0.6 | $3.6 | — | 262K | — |
| DevPass (LLM Gateway) | $0.6 | $3.6 | — | 262K | — |
| Hugging Face | $0.6 | $3.6 | — | 262K | Supported |
| Jalapeno Cloud | $0.6 | $3.6 | — | 262K | — |
| LLM Gateway | $0.6 | $3.6 | — | 262K | — |
| LLMTR | $0.6 | $3.6 | — | 256K | — |
| Mixlayer | $0.6 | $3.6 | — | 262K | — |
| NanoGPT | $0.6 | $3.6 | $0.3 | 258K | — |
| Nebius Token Factory | $0.6 | $3.6 | $0.06 | 262K | — |
| NovitaAI | $0.6 | $3.6 | — | 262K | — |
| Scaleway | $0.6 | $3.6 | — | 256K | — |
| Together AI | $0.6 | $3.6 | $0.35 | 262K | Supported |
| Cortecs | $0.668 | $4.01 | — | 262K | — |
| OVHcloud AI Endpoints | $0.71 | $4.25 | — | 262K | — |
| GreenPT | $0.798 | $4.959 | — | 262K | — |
| Qiniu | — | — | — | 256K | — |
Qwen3.5 397B-A17B — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare Qwen3.5 397B-A17B With
Qwen3.5 397B-A17B — Frequently Asked Questions
How much does Qwen3.5 397B-A17B cost?
Qwen3.5 397B-A17B costs $0.55 per 1M input tokens and $3.5 per 1M output tokens. This is mid-range pricing for its capability level.
What is the context window of Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B has a context window of 262K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B was created by Alibaba. It is classified as a open source model in our catalogue.
Is Qwen3.5 397B-A17B open source?
Yes, Qwen3.5 397B-A17B is an open-source model. The model weights are publicly available for download and self-hosting.