As of Nov 22, 2026, Inference lists 3 supported models in the Sovyron catalog, including Google Gemma 3, Llama 3.2 3B Instruct and Llama 3.2 1B Instruct across the gemma and llama families. The cheapest rate in the table is Llama 3.2 1B Instruct at $0.01 per 1M output tokens, the priciest Google Gemma 3 at $0.3. On a 3:1 input:output blend the metered rates span $0.01–$0.1875 per 1M tokens, and every price is Inference'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
3 of 3 models
Inference model prices in USD per 1M tokens, updated Nov 22, 2026