# I Built an OpenAI-Compatible Gateway to Control LLM Costs

> Source: <https://dev.to/qaz1214430044/i-built-an-openai-compatible-gateway-to-control-llm-costs-2ppm>
> Published: 2026-07-15 15:24:59+00:00

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.