Compare LLM API pricing across direct providers, OpenRouter, Groq, Together AI and Cerebras. Estimate monthly costs using caching, batch pricing, long-context rules, retries and other provider-specific pricing. Every listing links to its source, and LLMPrice tracks verified price changes over time.
I built LLMPrice because comparing LLM API prices became way more complicated than just looking at input and output token rates.
Caching, batch pricing, long-context rules, different endpoints and other provider-specific rules can change what you actually pay.
So I wanted one place where I could enter a real workload and compare the estimated monthly cost across models and providers.
Pricing is linked back to the original sources and updated automatically, and I’m also keeping a history of verified price changes over time.
It’s completely free and doesn’t require an account.
I’d really appreciate any feedback, especially if there’s a pricing rule, provider or model I’m missing.