Qwen/Qwen3.5-397B-A17B API
About
Build advanced reasoning agents with Qwen/Qwen3.5-397B-A17B, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.29/1M input and $1.74/1M output tokens, native tool calling support, open weights architecture. Access Qwen/Qwen3.5-397B-A17B via the SiliconFlow (China) API with up to 66K output tokens.
Capabilities
Input Modalities
textimagevideo
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.29
Output
$1.74
Frequently Asked Questions
Qwen/Qwen3.5-397B-A17B by SiliconFlow (China) costs $0.29 per 1M input tokens and $1.74 per 1M output tokens.
Model Details
ID
Qwen/Qwen3.5-397B-A17B
Provider
SiliconFlow (China)Family
qwen
Release Date
Feb 16, 2026
Knowledge Cutoff
Apr 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
SILICONFLOW_CN_API_KEY
API Base URL
https://api.siliconflow.cn/v1