As of Oct 4, 2026, STACKIT lists 8 supported models in the Sovyron catalog, including Qwen3.6 27B, Qwen3-VL Embedding 8B, GPT OSS 120B, GPT OSS 20B and Gemma 3 27B — qwen, gpt-oss, gemma, llama and mistral families. Its metered rates span $0.02–$1.8325 per 1M tokens on a 3:1 input:output blend, and every price in the table is STACKIT's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
8 of 8 models
STACKIT model prices in USD per 1M tokens, updated Oct 4, 2026