As of Oct 4, 2026, QiHang lists 9 supported models in the Sovyron catalog, including Gemini 2.5 Flash, Gemini 3 Flash Preview, GPT-5.2, GPT-5.2 Codex and Gemini 3 Pro Preview — gemini-flash, gpt, gpt-codex, gemini-pro, claude-opus and claude-haiku families. Its metered rates span $0.1025–$1.425 per 1M tokens on a 3:1 input:output blend, and every price in the table is QiHang's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
9 of 9 models
QiHang model prices in USD per 1M tokens, updated Oct 4, 2026