Qwen4 Max Launches on OpenRouter, Input Price Cut to $1.50 per Million Tokens
Qwen4 Max is now live on OpenRouter and is the first model in the Qwen4 series, targeting coding, office, and long-horizon agent tasks. Its pricing is $1.50 per million input tokens and $4.50 per million output tokens, lower than Qwen3.8 Max's $2 and $6, with cache hits at $0.075 per million tokens and a 1M context window. The model supports text, image, and video inputs, and offers tool calling and structured output.
Why read this
AI score 75
The source provides Qwen4 Max's pricing and input modalities on OpenRouter, which can be used to compare its cost changes against Qwen3.8 Max.
Topics
Body
Pricing is $1.50/M input and $4.50/M output, down from $2/$6 on Qwen3.8 Max, with $0.075/M cache hits and 1M context.
Text, image and video input, with tool calling and structured outputs.
See more: https://t.co/l5WEKF2nPp