Cerebras Inference
cerebras.ai
Ultra-fast inference API for selected open models
- Free tier
- Yes
- Per month
- Free – Usage
- MCP
- No
Why it's here
Fast inference and a permanent free allocation make prototyping attractive; production throughput requires a paid tier.
Free tier
$5 free credit after verified payment method; expires in 30 days
Visit Cerebras Inference(opens in a new tab)
Last verified
LLM APIs
#10 of 20Fast inference and a permanent free allocation make prototyping attractive; production throughput requires a paid tier.
| per month | FreeFree1M tokens/day free permanently, no credit card | DeveloperUsagePay per token from $0.10 to $2.00 per 1M tokens | EnterpriseCustomDedicated CS-3 wafer-scale systems and custom SLAs |
|---|---|---|---|
| Commercial use | |||
| Tool calling | |||
| OpenAI-compatible | |||
| No data training | |||
| Prod rate limits | |||
| JSON schema | |||
| Prompt caching | |||
| Image input | |||
| Context window | 128000 tokens | 128000 tokens | 128000 tokens |