---
id: "nr-openai-adds-per-task-and-per-subagent-usage-analytics-0f7088"
slug: "openai-adds-per-task-and-per-subagent-usage-analytics-0f7088"
title: "OpenAI adds per-task and per-subagent usage analytics to Codex app"
observed_at: "2026-09-18T13:48:49+00:00"
record_date: "2026-09-18"
date_kind: "observed_at"
novelty: "new"
source_platform: "x.com"
topics: ["coding-agents","developer-tools"]
entities: ["OpenAI","Codex"]
related_patterns: []
source_url: "https://x.com/OpenAIDevs/status/2100733364877803741"
source_urls: ["https://x.com/OpenAIDevs/status/2100733364877803741"]
basket: {"id":"0325e6b8-f527-4f9b-bfa3-3f30e57f380b","revision":1,"cluster_id":"0f7088c6-c59b-4298-baeb-1e04b1c5c751"}
type: "raw_signal"
description: "OpenAI added usage analytics to the Codex desktop app that break down how tasks, subagents, and individual chats contribute to Codex usage."
why_it_matters: "For engineers running parallel agents, attribution by task and subagent shows which workflows consume the most quota, so delegation patterns can be adjusted with data. The post does not describe any change to usage limits or pricing, or whether the same data is available through an API."
verification_level: "source-inspected"
signal_type: "newsroom_basket_signal"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:openai-adds-per-task-and-per-subagent-usage-analytics-0f7088"
retrieval_nugget: "OpenAI added usage analytics to the Codex desktop app that break down how tasks, subagents, and individual chats contribute to Codex usage. OpenAI Developers announced usage analytics for Codex that show how tasks, subagents, and individual chats contribute to a user's Codex usage. The analytics are in the desktop app under Settings, in Usage & billing for personal and Business"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/openai-adds-per-task-and-per-subagent-usage-analytics-0f7088/","markdown":"https://newruntime.com/signals/openai-adds-per-task-and-per-subagent-usage-analytics-0f7088.md","json":"https://newruntime.com/signals/openai-adds-per-task-and-per-subagent-usage-analytics-0f7088.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# OpenAI adds per-task and per-subagent usage analytics to Codex app

## Retrieval answer

OpenAI added usage analytics to the Codex desktop app that break down how tasks, subagents, and individual chats contribute to Codex usage. OpenAI Developers announced usage analytics for Codex that show how tasks, subagents, and individual chats contribute to a user's Codex usage. The analytics are in the desktop app under Settings, in Usage & billing for personal and Business

OpenAI Developers announced usage analytics for Codex that show how tasks, subagents, and individual chats contribute to a user's Codex usage. The analytics are in the desktop app under Settings, in Usage & billing for personal and Business accounts or in Usage for eligible Enterprise accounts, and require the latest app version.

For engineers running parallel agents, attribution by task and subagent shows which workflows consume the most quota, so delegation patterns can be adjusted with data. The post does not describe any change to usage limits or pricing, or whether the same data is available through an API.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Coding Agents](https://newruntime.com/topics/coding-agents.md): Explore the coding-agents topic hub.
- topic hub: [Developer Tools](https://newruntime.com/topics/developer-tools.md): Explore the developer-tools topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)