As of Nov 22, 2026, RunInfra lists 6 supported models in the Sovyron catalog, including Step 5 Preview, GLM-5.3-Flash, Ornith 1.5 35B A3B, GLM-5.3 and Qwen3.8 27B across the step, glm-flash, ornith, glm, qwen and nemotron-lightning families. The cheapest rate in the table is Nemotron 3.5 Lightning 30B A3B at $0.15 per 1M output tokens, the priciest GLM-5.3 at $4.2. On a 3:1 input:output blend the metered rates span $0.075–$2.025 per 1M tokens, and every price is RunInfra'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
6 of 6 models
RunInfra model prices in USD per 1M tokens, updated Nov 22, 2026