QiHang
5 modelsProvider docs
As of Nov 22, 2026, QiHang lists 5 supported models in the Sovyron catalog, including Gemini 3 Flash Preview, Gemini 3 Pro Preview, Claude Haiku 4.5, GPT-5 Mini and Gemini 2.5 Flash across the gemini-flash, gemini-pro, claude-haiku and gpt-mini families. The cheapest rate in the table is GPT-5 Mini at $0.29 per 1M output tokens, the priciest Gemini 3 Pro Preview at $3.43. On a 3:1 input:output blend the metered rates span $0.1025–$1.285 per 1M tokens, and every price is QiHang's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
5 of 5 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| Gemini 3 Flash Preview | $0.07 | $0.43 | — | 1.0M | Dec 17, 2025 |
| Gemini 3 Pro Preview | $0.57 | $3.43 | — | 1.0M | Nov 18, 2025 |
| Claude Haiku 4.5 | $0.14 | $0.71 | — | 200k | Oct 15, 2025 |
| GPT-5 Mini | $0.04 | $0.29 | — | 200k | Aug 7, 2025 |
| Gemini 2.5 Flash | $0.09 | $0.71 | — | 1.0M | Jun 17, 2025 |