As of Nov 22, 2026, Cerebras lists 2 supported models in the Sovyron catalog, including Qwen3.8 27B and GPT OSS 120B across the qwen and gpt-oss families. The cheapest rate in the table is GPT OSS 120B at $0.75 per 1M output tokens, the priciest Qwen3.8 27B at $1.49. On a 3:1 input:output blend the metered rates span $0.45–$1.115 per 1M tokens, and every price is Cerebras'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
2 of 2 models
Cerebras model prices in USD per 1M tokens, updated Nov 22, 2026