Cerebras models and pricing
We track 2 models on Cerebras from 2 labs. The cheapest paid model is gpt-oss-120b, at $0.35 per million input tokens and $0.75 per million output tokens. Input prices range from $0.35 to $0.99 and output prices from $0.75 to $1.49 per million tokens. The largest context window is 131K tokens (Qwen3.8 27B and gpt-oss-120b). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on Cerebras
- gpt-oss-120b$0.35 / $0.75
- Qwen3.8 27B$0.99 / $1.49
Input / output per million tokens, paid models, by combined price.
All Cerebras models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| Qwen3.8 27B qwen-3.8-27b | Alibaba (Qwen) | $0.99 | $1.49 | 131K | models.dev |
| gpt-oss-120b gpt-oss-120b | OpenAI | $0.35 | $0.75 | 131K | models.dev |
Frequently asked questions
How much does Cerebras cost per million tokens?
Prices on Cerebras depend on the model. Across the 2 models we track, input costs $0.35 to $0.99 per million tokens and output costs $0.75 to $1.49 per million tokens. Prices last verified 18 Nov 2026.
What is the cheapest model on Cerebras?
gpt-oss-120b from OpenAI is the cheapest paid model we track on Cerebras, at $0.35 per million input tokens and $0.75 per million output tokens. Next are Qwen3.8 27B ($0.99 / $1.49). Prices last verified 18 Nov 2026.
How many models does Cerebras offer?
We currently track 2 active models on Cerebras from 2 labs, led by Alibaba (Qwen) (1) and OpenAI (1).
Which model on Cerebras has the largest context window?
Qwen3.8 27B and gpt-oss-120b share the largest context window we track on Cerebras: 131,072 tokens (131K).