Cerebras API pricing
2 models · USD per 1M tokens · verified 2026-10-23
Cerebras serves 2 of the models we track, 2 of them open-weights. The cheapest is GPT OSS 120B at $0.35 input and $0.75 output per million tokens. For 0 of these models, Cerebras is the cheapest tracked host.
// models on Cerebras
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| GPT OSS 120B | OpenAI | $0.35 | $0.75 | 131.1K | +540.1% |
| Qwen3.8 27B | Alibaba (Qwen) | $0.99 | $1.49 | 262.1K | +43.9% |
// how to read this page
Prices are Cerebras's base-tier list prices per million tokens. "vs best price" compares Cerebras's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.