Cerebras Cloud Serverless AI Token Pricing & API Rates
Verified RatesWafer-Scale Hardware CloudReal-time verified rates (Updated 2026)
Cerebras Cloud Serverless AI Token Pricing (4 Models)
| Model | Category | Cold Start | Context | Input ($/1M or Unit) | Output / 1M Tokens | Speed | Actions |
|---|---|---|---|---|---|---|---|
| Llama-3.1-8B-Instant | LLM | 0s Instant | 128K | $0.10 | $0.10 | 2150 tps | API Docs |
| Llama-3.3-70B-Instruct | LLM | 0s Instant | 128K | $0.60 | $0.60 | 1850 tps | API Docs |
| Qwen-2.5-72B-Instruct | LLM | 0s Instant | 128K | $0.60 | $0.60 | 1750 tps | API Docs |
| DeepSeek-R1-Distill-Llama-70B | REASONING | 0s Instant | 128K | $0.65 | $0.65 | 1800 tps | API Docs |
Simulate monthly input and output token volume on Cerebras Cloud and compare your savings against OpenAI GPT-4o and Claude 3.5.
Open Cerebras Cloud Cost CalculatorCompare alternative inference platforms like Groq, Together AI, and DeepInfra on token latency, context windows, and pricing.
View Alternatives ComparisonCerebras Cloud Pricing FAQ & Cost Guide
How does serverless token billing work on Cerebras Cloud?
Cerebras Cloud meters exact input (prompt) and output (completion) tokens. You only pay for what your application generates. There is zero baseline server provisioning cost or ongoing hourly commitment.
Does Cerebras Cloud charge for stopped instances or idle storage?
No. Cerebras Cloud is a purely serverless platform. When your application receives zero traffic, your hourly billing is strictly $0.00. There are no persistent disk fees or stopped instance retention charges.
Are there hidden egress or bandwidth fees?
Egress on Cerebras Cloud is billed at Free / Included in Token Rate.
What payment methods does Cerebras Cloud accept?
Cerebras Cloud accepts standard credit card billing and enterprise invoicing with verified business accounts.