[Feature] UI - Usage: Model Breakdown Per Key

[yuneng-jiang]

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

CI (LiteLLM team)

CI status guideline:

• 50-55 passing tests: main is stable with minor issues.
• 45-49 passing tests: acceptable but needs attention
• <= 40 passing tests: unstable; be careful with your merges and assess the risk.

• Branch creation CI run
  Link:

• CI run for the last commit
  Link:

• Merge / cherry-pick CI run
  Links:

Type

🆕 New Feature
✅ Test

Changes

Adds a model usage breakdown view for individual API keys in the dashboard. When viewing activity metrics for a specific API key, users can now see which models were used, along with spend, request counts, and token usage per model. The feature includes a new KeyModelUsageView component that displays data in both table and chart formats, with toggleable view modes. Data processing logic aggregates model breakdowns from daily activity data for each API key, sorted by spend.

Screenshots

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
litellm	Error		Jan 30, 2026 2:33am