Qwen
Qwen3.5 397b A17b
qwen/qwen3.5-397b-a17b
262.1K context·65.5K max output·text+image+video->text
Input
$0.3900
per 1M tokens
Output
$2.34
per 1M tokens
Cache Read
-
not available
Cache Write
-
not available
Quality Benchmarks
FrontierValue: 151.6
Coding
Code generation, completion, debugging
Math
Competition math, calculus, olympiad
Reasoning
Logic, spatial, puzzle solving
Language
Summarization, paraphrase, writing
Overall
Source: LiveBench (livebench.ai) / Scores 0-100
Capabilities
VisionTool UseReasoningPrompt Caching
Similar Price Range
More from Qwen
Deploy your AI agent for $33/mo flat.
Managed Telegram bot hosting. We handle the infrastructure.
Any model. Any channel. Zero infrastructure.