LLM Gateway

LLM Gateway is an open-source API gateway that sits between your apps and LLM providers. One integration gives you access to 180+ models from 60+ providers—and the visibility to control costs.

• Route: Switch between OpenAI, Anthropic, Google, and 60+ other providers without changing your code
• Manage: One dashboard for all your API keys—no more scattered credentials
• Observe: Track every request's cost, latency, and token usage in real-time
• Optimize: Compare models side-by-side to find the best price-to-performance ratio

Why LLM Gateway?

If you've built with multiple LLM providers, you know the pain: different SDKs, scattered API keys, no unified view of what you're spending. LLM Gateway gives you a single API that works with any provider—and a dashboard that shows exactly where your money goes.

One Compatible Endpoint

Already using OpenAI's SDK? Keep your code. Just change the base URL:

1curl -X POST https://api.llmgateway.io/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
4  -d '{
5    "model": "gpt-4o",
6    "messages": [{"role": "user", "content": "Hello, how are you?"}]
7  }'

1curl -X POST https://api.llmgateway.io/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
4  -d '{
5    "model": "gpt-4o",
6    "messages": [{"role": "user", "content": "Hello, how are you?"}]
7  }'

See Every Request, Every Dollar

Every API call is tracked with:

• Cost per request — Know exactly what each prompt costs
• Latency breakdowns — See response times by model and provider
• Error rates — Spot reliability issues before they hit production
• Token usage — Track input and output tokens across all requests

No more guessing where your AI spend goes. Compare models head-to-head and make data-driven decisions.

Ready to try it? Get started free — no credit card required.