Ollama Herd

Tagged Requests
-
Unique Tags
-
Top Tag
-

Requests by Tag

Tag Activity Over Time

Tag Requests Avg Latency Avg TTFT Prompt Tokens Completion Tokens Error Rate

How to tag requests

Add tags to your requests so they appear here. Tags are stripped before reaching Ollama.

OpenAI SDK (Python)
client.chat.completions.create(
  model="llama3.2:3b",
  messages=[...],
  extra_body={"metadata": {"tags": ["my-app"]}}
)
Header-based
curl http://router:11435/api/chat \
  -H "X-Herd-Tags: my-app, prod" \
  -d '{"model": "...", "messages": [...]}'