Price list compares per-million-token costs across Qwen API models

On October 23, 2026, a DEV Community post published a price comparison covering every Qwen model on the Qwen API, quoted per million tokens. The list sets out three billing rates for each model — input, cached input and output — and places the author's own platform pricing side by side with the list prices shown on Qwen's official page.

The cheapest entry in the list is Qwen3.7 Plus, at $0.192 for input and $0.768 for output. According to the post, output typically costs between three and seven times input depending on the model: roughly three times on Qwen3.7 Max and close to seven times on Qwen3.6 27B. The article also estimates what a single chat turn and a long-document request would cost on three models — Qwen3.7 Max, Qwen3.7 Plus and Qwen3.6 27B.

On billing mechanics, the post explains that Qwen API calls are charged per token across three rates per million tokens: input, cached input and output. The cost of a request is its token count multiplied by the rates of the model it names. The material does not discuss what prompted the comparison, nor any reactions or later changes; the public information currently stops at the list itself.