
Cerebras Inference API pricing
Cerebras Inference has 1 model with a token price on record: input $0.35 and output $0.75 per million tokens at the standard tier. Each rate links to the page it was read from, most recently on 2026-10-22.
Cerebras Inference sells models made by others, so these are what it charges, not the makers' own prices.
Price a workload on these models →Every seller →Cerebras Inference’s own pricing page →
Every model Cerebras Inference prices
| Model | Tier | Input $/M | Output $/M | Cached $/M | Context | Read from |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | Standard | $0.35 | $0.75 | ○ | 131K | 2026-10-22 |
○ means no answer on record, not zero. Rates older than 21 days are hidden rather than shown stale. Input and output are priced separately, so a figure built from input alone is a different, smaller number.
Other sellers
OpenRouter 385Novita AI 65Together AI 20Anthropic 19Baseten 16Fireworks AI 13OpenAI 13Mistral AI 10FriendliAI 7Google DeepMind 7SambaNova 6Moonshot AI 4AI21 Labs 2DeepSeek 2xAI 1
Frequently asked
How much does the Cerebras Inference API cost per million tokens?
Does Cerebras Inference price cached input or a batch tier?
Where do these Cerebras Inference prices come from?
How these prices are read
Every rate here links to the page it was read from and carries the date it was read. Nothing is averaged or estimated, and a rate we have not read is shown as missing instead of guessed. How any figure is gathered, and what is refused, is on methodology.