Skip to content
Sovyron

Wafer

5 modelsProvider docs

As of Oct 4, 2026, Wafer lists 5 supported models in the Sovyron catalog, including GLM-5.2, GLM5.2-Fast, MiniMax-M3, Kimi K2.6 and GLM-5.1 — glm, minimax and kimi-k2 families. Its metered rates span $0.5775–$4.8125 per 1M tokens on a 3:1 input:output blend, and every price in the table is Wafer's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

5 of 5 models
Wafer model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
GLM-5.2$1.2$4.1$0.21.0MJun 13, 2026
GLM5.2-Fast$3$10.25$0.51.0MJun 13, 2026
MiniMax-M3$0.33$1.32$0.071.0MJun 1, 2026
Kimi K2.6$1.14$4.8$0.19262kApr 21, 2026
GLM-5.1$1$3.2$0.1203kApr 7, 2026