---
type: "post"
id: "response-speed-and-usage-resets-in-work-and-a51cd3"
slug: "response-speed-and-usage-resets-in-work-and-a51cd3"
title: "Response speed and usage resets in Work and Codex"
description: "OpenAI has published Help Center guidance saying that GPT-6 Astra and GPT-6.1 Sol produce text roughly 50% faster at the default speed setting."
retrieval_nugget: "OpenAI has published Help Center guidance saying that GPT-6 Astra and GPT-6.1 Sol produce text roughly 50% faster at the default speed setting."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["codex"]
entities: ["OpenAI","ChatGPT","Codex","GPT-6 Astra","GPT-6.1 Sol","OpenCode","Devin"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Adds help guidance that GPT-6 Astra and GPT-6.1 Sol produce text roughly 50% faster by default, while clarifying that end-to-end task times may not improve and resets/speed settings are separate."
prior_refs: ["memory:82788ad8-64bd-8453-ae36-2ee51feb54d0","memory:71bc5b09-54e2-8acd-a644-5dfff4853df2"]
source_url: "https://help.openai.com/en/articles/20001596-response-speed-and-usage-resets-in-work-and-codex"
source_urls: ["https://help.openai.com/en/articles/20001596-response-speed-and-usage-resets-in-work-and-codex"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:response-speed-and-usage-resets-in-work-and-a51cd3"
status: "published"
visuals: []
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"]}
routes: {"html":"https://newruntime.com/posts/response-speed-and-usage-resets-in-work-and-a51cd3/","markdown":"https://newruntime.com/posts/response-speed-and-usage-resets-in-work-and-a51cd3.md","json":"https://newruntime.com/posts/response-speed-and-usage-resets-in-work-and-a51cd3.json"}
---

# Response speed and usage resets in Work and Codex

## Retrieval answer

OpenAI has published Help Center guidance saying that GPT-6 Astra and GPT-6.1 Sol produce text roughly 50% faster at the default speed setting.

OpenAI has published Help Center guidance saying that GPT-6 Astra and GPT-6.1 Sol produce text roughly 50% faster at the default speed setting. The stated improvement applies when a ChatGPT subscription is used in OpenAI products or supported partner apps, including OpenCode, Pi, Amp, and Devin.

Users on Go, Plus, or Pro can use their ChatGPT plan in supported partner apps by signing in with ChatGPT and selecting that plan for AI requests. OpenAI says the default improvement does not require enabling Fast or Ultrafast; those remain separate settings with their own availability and usage rates.

The guidance distinguishes text-generation speed from end-to-end task time in Work and Codex. Tasks may still take time for reasoning, tool use, multiple steps, or approval waits. It also says promotional usage resets are offer-specific, are not guaranteed daily, and are not automatically granted with a speed improvement. The source does not provide benchmark methodology, a baseline latency figure, or a guarantee that an individual task or account will experience a measurable overall speedup.

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: [Codex](https://newruntime.com/topics/codex.md): Explore the codex topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- 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)