As of Nov 18, 2026, Infomaniak lists 8 supported models in the Sovyron catalog, including Apertus v1.5 70B, Kimi K2.6, Gemma 4 31B IT, Mistral Small 4 and Qwen3.5 397B-A17B FP8 across the kimi-k2, gemma, mistral-small, qwen, ministral and bge families. The cheapest rate in the table is Gemma 4 31B IT at $0.5 per 1M output tokens, the priciest Qwen3.5 397B-A17B FP8 at $4.46. On a 3:1 input:output blend the metered rates span $0.06–$1.8575 per 1M tokens, and every price is Infomaniak's own, normalized to USD. Offer mix: 1 free-tier offer. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
8 of 8 models
Infomaniak model prices in USD per 1M tokens, updated Nov 18, 2026