🇨🇳 Chinese model
Qwen3.5 397B-A17B
Text Image Video Function calling Reasoning
Pricing & specs
Input / 1M tokens $0.43
Output / 1M tokens $2.58
Cache / 1M tokens —
Context window 262K tokens
Max output 66K tokens
Updated 2026-02-16
Docs Official docs ↗
Price source View source ↗
Providers
USD / 1M tokens · input / output
Alibaba Cloud Official $0.43 / $2.58 SiliconFlow (China) lowest $0.29 / $1.74 Vultr $0.30 / $2.00 SiliconFlow $0.39 / $2.34 Deep Infra $0.45 / $3.00 Jalapeno Cloud $0.60 / $3.60 Hugging Face $0.60 / $3.60 2 more at higher prices
Similar models · Top 5
Mistral Medium 3.1 🇫🇷 262K In $0.40 · Out $2.00 · Cache — Moonshot Kimi K2.5 🇨🇳 262K In $0.57 · Out $2.41 · Cache — Kimi K2 0905 🇨🇳 262K In $0.60 · Out $2.50 · Cache $0.15 Moonshot Kimi K2 Thinking 🇨🇳 262K In $0.57 · Out $2.29 · Cache — GLM-5 🇨🇳 203K In $0.60 · Out $2.68 · Cache $0.15
Want to go deeper on AI and cloud cost management?
Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.