Compare Helicone’s Proxy and Async integration methods. Understand the features, benefits, and use cases for each approach to choose the best fit for your LLM application.
Proxy | Async | |
---|---|---|
Easy setup | ✅ | ❌ |
Prompts | ✅ | ✅ |
Prompts Auto Formatting (easier) | ✅ | ❌ |
Custom Properties | ✅ | ✅ |
Bucket Cache | ✅ | ❌ |
User Metrics | ✅ | ✅ |
Retries | ✅ | ❌ |
Custom rate limiting | ✅ | ❌ |
Open-source | ✅ | ✅ |
Not on critical path | ❌ | ✅ |
0 Propagation Delay | ❌ | ✅ |
Negligible Logging Delay | ✅ | ✅ |
Streaming Support | ✅ | ✅ |
Proxy: flow of data.
Here's a simple example
api.openai.com
, you will change the URL to a Helicone dedicated domain oai.helicone.ai
.You can also use the general Gateway URL gateway.helicone.ai
if Helicone doesn’t have a dedicated domain for the provider yet.Async: flow of data.
Need more help?