Cerebras API Pricing (Oct 2026): All 7 Models per 1M Tokens
As of : 7 models tracked. The median price is $0.60 per 1M input tokens and $0.80 per 1M output tokens. Cheapest blended price: llama3.1-8b (Cerebras, $0.10 per 1M input / $0.10 per 1M output).
API list prices for every Cerebras chat model we track.
Models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| llama3.1-8b | Cerebras | $0.10 | $0.10 | — | 128K |
| gpt-oss-120b | Cerebras | $0.35 | $0.75 | — | 131K |
| qwen-3-32b | Cerebras | $0.40 | $0.80 | — | 128K |
| llama3.1-70b | Cerebras | $0.60 | $0.60 | — | 128K |
| llama-3.3-70b | Cerebras | $0.85 | $1.20 | — | 128K |
| gemma-4-31b | Cerebras | $0.99 | $1.49 | — | 131K |
| qwen-3.8-27b | Cerebras | $0.99 | $1.49 | — | 66K |
FAQ
How are prices shown?
In US dollars per 1 million tokens, as listed for each model's API. 'Blended' assumes 3 input tokens for every output token.
Which model is cheapest here?
llama3.1-8b from Cerebras, at $0.10 per 1M input and $0.10 per 1M output tokens (as of ).
How current are these prices?
We copy the open-source LiteLLM price list once a day and record every change. Providers can change prices at any time, so confirm on the official pricing page linked from each model.