About InferPrice
InferPrice compares what GPU clouds and LLM APIs charge, and publishes practical, tested articles for engineers who deploy and pay for inference. It's an independent project: no provider pays to be listed or ranked.
What you'll find here
- GPU and API price tables from 12 providers, refreshed daily from each provider's own public pricing page. A price is shown only if it appears on that page the day we check; nothing is estimated or carried forward, and every row links to its source.
- Articles every few days on LLM inference, LLMOps and AI agents. Their code is tested, their claims are checked against primary sources, and GPU behaviour is measured on real hardware.
- The break-even calculator: renting GPUs against paying per token.
- The LLM exposure check: a one-minute script that shows whether your own Ollama, vLLM or MCP server is open to the internet.
- A free price report for your own token volume.
Contact and support
Email inference.price.support@gmail.com with questions, a price that looks wrong (include the link to the provider's pricing page), or anything about endpoint monitoring, including cancellations and refunds. Monitoring customers can also reply to any monitoring email.