Models & APIs / Cerebras Inference API pricing Verified 9 Nov 2026, 12:00 UTC Source inference-docs.cerebras.ai model pages
Cerebras Inference API pricing
by Cerebrasper 1M tokens
$0.75 / 1M outputgpt-oss-120B (Cerebras) · the cheapest model
Cerebras Inference API costs $0.35–$0.99 per 1M input tokens and $0.75–$1.49 per 1M output tokens. Output tokens cost several times more than input, so long answers drive the bill. Cerebras sells API access only; there is no chat subscription.
Cheapest output$0.75gpt-oss-120B (Cerebras) · per 1M
Top model$1.49Qwen 3.8 27B (Cerebras) · per 1M output
Every model, per 1M tokens
USD list price, before batch or volume discounts| Model | Input | Output | Cached input | Context |
|---|---|---|---|---|
| gpt-oss-120B (Cerebras) | $0.35 | $0.75 | — | 131K |
| Qwen 3.8 27B (Cerebras) | $0.99 | $1.49 | — | 128K |
What will you pay?
$44.60
per month on Qwen 3.8 27B (Cerebras)
Prices from inference-docs.cerebras.ai model pages How we collect prices Some links are affiliate links; they never change the prices or the order shown. Disclosure