Pricing

Simple, transparent pricing that scales with your needs

Perfect for individuals and small projects

$0forever

Unlimited LLM requests

Rate Limit: 6 RPM, 20,000 TPM

Model: gpt-4.1, gemini-2.5-pro, gemini-2.5-flash, deepseek-r1

Geo-distributed LLM Providers with low latency

MCP & Function Calling Tools deployments

1-day API access log retention

Email support

Limited to basic features and models

Ideal for growing teams and businesses

$25/month

All Free plan features

Models: gpt-4.1, gemini-2.5-pro, gemini-2.5-flash, deepseek-r1, deepseek-v3, Claude, Groq, Cerebras and more

Rate Limit: 5,000 RPM, 800,000 TPM

MCP & Function Calling Tools deployments

LLM API and Tools Call latency breakdown

World traffic insights

90-day API access log retention

Advanced support