As of Oct 4, 2026, Berget.AI lists 6 supported models in the Sovyron catalog, including GLM-5.3-Flash, Qwen3.8 27B, Kimi K3, GLM-5.2 and Gemma 4 31B Instruct — glm-flash, qwen, kimi-k3, glm, gemma and mistral-small families. Its metered rates span $0.33–$6 per 1M tokens on a 3:1 input:output blend, and every price in the table is Berget.AI's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
6 of 6 models
Berget.AI model prices in USD per 1M tokens, updated Oct 4, 2026