As of Oct 4, 2026, Cerebras lists 2 supported models in the Sovyron catalog, including Qwen3.8 27B and GPT OSS 120B — qwen and gpt-oss families. Its metered rates span $0.45–$1.115 per 1M tokens on a 3:1 input:output blend, and every price in the table is Cerebras's own, normalized to USD — 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 Oct 4, 2026