@ArizePhoenix: Phoenix 17.7.0 makes your token usage legible. New token detail charts break prompt + completion tokens into their part…
Summary
Phoenix 17.7.0 adds token detail charts that break down prompt and completion tokens into subcategories, with pan, zoom, and live-stream capabilities for better observability of AI model token usage.
View Cached Full Text
Cached at: 06/18/26, 10:06 AM
Phoenix 17.7.0 makes your token usage legible.
New token detail charts break prompt + completion tokens into their parts, over time: • Prompt → input, cache read, cache write, audio • Completion → output, reasoning, audio
See your cache read rates and watch reasoning-token usage trend as you tune models and thinking budgets - whatever parts your model reports, plotted as their own series.
And you can now pan, zoom & live-stream any time range right from the dashboard toolbar - no reopening the picker.
Similar Articles
@DataChaz: STOP BURNING YOUR TOKENS! If you use Claude Code, you are probably wasting 80% of your context window. I found 10 ace t…
A tweet thread by @DataChaz lists 10 open-source tools to drastically reduce token usage in Claude Code and similar AI coding assistants, potentially cutting API bills by 75-98% through various optimizations.
@ArizePhoenix: When debugging agents, you need to get to the problematic issues QUICKLY! Phoenix now comes with quick list-details nav…
Arize Phoenix adds quick list-details navigation and resizable drawers for faster agent conversation debugging, plus VIM support in sessions.
@ArizePhoenix: Something we’ve been playing with and liking a lot: Give every coding agent its own observability stack. Because Arize …
Arize Phoenix enables local-first, air-gapped observability for coding agents, allowing each agent to have its own traces, evals, and feedback loop for self-verification.
AI agents are making tokenization platforms far more usable than I expected
A developer shares how AI agents are improving tokenization platforms through intelligent orchestration of humans and systems, rather than full autonomy.
@HaydnBelfield: The main benefit of hearing about tokenmaxxing experiments and token leaderboards seems to be an inspirational/explorat…
Haydn Belfield discusses how tokenmaxxing experiments and token leaderboards serve an inspirational and exploratory purpose by testing AI model limits and discovering new workflows.