[GH-ISSUE #12467] Ollama Metrics Port #34043

Closed
opened 2026-04-22 17:16:14 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @luculli on GitHub (Oct 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12467

🎯 Feature Request: Metrics Endpoint for Model Usage

Issue:

Add a dedicated port/endpoint in Ollama that exposes usage metrics for each model (e.g., total tokens, requests, latency, error rates).

🔍 Why this matters

  • Performance monitoring: Allows developers to identify bottlenecks or under‑utilized models.
  • Capacity planning: Helps in scaling decisions by showing usage trends.
  • Research & debugging: Enables quick insight into how models behave under load.
Originally created by @luculli on GitHub (Oct 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12467 ## 🎯 **Feature Request: Metrics Endpoint for Model Usage** Issue: Add a dedicated port/endpoint in Ollama that exposes usage metrics for each model (e.g., total tokens, requests, latency, error rates). 🔍 Why this matters - Performance monitoring: Allows developers to identify bottlenecks or under‑utilized models. - Capacity planning: Helps in scaling decisions by showing usage trends. - Research & debugging: Enables quick insight into how models behave under load.
GiteaMirror added the feature request label 2026-04-22 17:16:14 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34043