Skip to content
Sovyron

Kosmik Compute

1 modelsProvider docs

As of Nov 22, 2026, Kosmik Compute lists 1 supported model in the Sovyron catalog, including Qwen3.8 27B across the qwen families. The cheapest rate in the table is Qwen3.8 27B at $2.2 per 1M output tokens. On a 3:1 input:output blend the metered rates sit at $0.8125 per 1M tokens, and every price is Kosmik Compute'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

1 of 1 models
Kosmik Compute model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Qwen3.8 27B$0.35$2.2$0.09262kAug 14, 2026