I Built an OpenAI-Compatible Gateway to Control LLM Costs

An indie developer built CostLLM, an OpenAI-compatible API gateway that sits between code and LLM providers to control costs. The gateway offers per-project spending visibility, cost caps per feature, and rate limit management without vendor lock-in. It supports models like deepseek-v4-flash, deepseek-v4-pro, deepseek-chat, and deepseek-reasoner.

As an indie developer building AI products, I kept hitting the same wall: how do I control LLM costs without vendor lock-in? Direct API keys meant zero visibility into per-project spending. Month-end surprise bills. No way to cap costs per feature. Rate limit headaches. So I built CostLLM — an OpenAI-compatible API gateway that sits between your code and the LLM provider. Before client = OpenAI api key="sk-proj-..." After client = OpenAI base url="https://api.costllm.ai/v1", api key="YOUR COSTLLM API KEY" | Model | Type | |---|---| | deepseek-v4-flash | Fast chat | | deepseek-v4-pro | Complex reasoning | | deepseek-chat | General purpose | | deepseek-reasoner | Deep analysis | Building a production API gateway taught me a lot about concurrency, streaming, error handling, and payment webhooks. The hardest part wasn't the code — it was designing a pricing model that works for both free users and growing teams. I'd love feedback from other developers working with LLM APIs — especially around cost visibility, key management, and what you'd want from a gateway.