Cerebras pricing - 2026
Cerebras API starts at $0.100/1M input tokens. Prices effective since April 30, 2026.
| Model | Input $/1M | Output $/1M | Notes |
|---|---|---|---|
| Llama 3.3.70b | $0.850 | $1.20 | |
| Llama3.1.70b | $0.600 | $0.600 | |
| Llama3.1.8b | $0.100 | $0.100 | |
| Gpt Oss 120b | $0.350 | $0.750 | |
| Qwen 3.32b | $0.400 | $0.800 | |
| Zai Glm 4.6 | $2.25 | $2.75 | |
| Zai Glm 4.7 | $2.25 | $2.75 |
Prices effective since April 30, 2026. Verified June 4, 2026. Confirm at LiteLLM before billing.
Cost calculator
Estimated monthly cost · 70% input / 30% output split
+1 more models not shown
Price history
Input price per 1M tokens - tracked from Apr 30, 2026
Prices scraped daily from official provider documentation. Chart shows input token pricing.
Related pages
About Cerebras API pricing
Cerebras API pricing is set by Cerebras Systems and billed per million tokens processed. Input tokens (your prompt) and output tokens (the response) are priced separately.
Prices on this page are sourced from official Cerebras Systems documentation and updated when Cerebras announces pricing changes. Check the official Cerebras pricing page for the most current rates.
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries - every Monday. Free.