LiteLLM · python
from litellm import completion
import os
completion(
model="openai/gpt-4o-mini",
api_base="https://intertrace.fly.dev/v1",
api_key=os.environ["INTERTRACE_RUNTIME_API_KEY"],
messages=[{"role": "user", "content": "Hello"}],
)api_base → Intertrace /v1 with openai/ model prefix.
+Three steps
- 01
Get a runtime key
Create an itr_rt_* key in Connect. It carries your tenant, so no org headers are needed.
- 02
Point the client at Intertrace
Paste the snippet. Nothing else in your code changes.
- 03
Watch decisions arrive
Every call shows up in Traffic with its verdict and the reason, in monitor mode first.
+What you get
Once it's connected
- Prompt injection and instruction override caught before the model sees it
- Sensitive data kept out of prompts and responses
- Tool calls authorized before they execute
- Every decision logged with its reason, per agent
+Related
+ The AI watching your AI
Protect your LiteLLM agents today.
Start in monitor mode, see every decision, then turn on enforcement when you're ready.