---
id: "nr-reported-gpt-6-1-sol-and-astra-in-codex-may-reach-about-50-tokens-per-298ba3"
slug: "reported-gpt-6-1-sol-and-astra-in-codex-may-reach-about-50-tokens-per-298ba3"
title: "Reported: GPT-6.1 Sol and Astra in Codex may reach about 50 tokens per second"
observed_at: "2026-10-06T08:05:43.637Z"
record_date: "2026-10-06"
date_kind: "observed_at"
novelty: "new"
source_platform: "x.com"
topics: ["rumors","ai-products"]
entities: []
related_patterns: []
source_url: "https://pc.watch.impress.co.jp/docs/news/2145903.html"
source_urls: ["https://pc.watch.impress.co.jp/docs/news/2145903.html","https://pagewatcher.app","https://x.com/actu_ia/status/2107365241256358299","https://x.com/Angaisb_/status/2107372248365449612"]
type: "raw_signal"
description: "Posts on X and a PC Watch report say GPT-6.1 Sol and GPT-6 Astra are reportedly running about 50% faster, at roughly 50 tokens per second rather than around 30."
why_it_matters: "If sustained, faster output could shorten waits for Codex users; the reported speeds may vary, and posts describe uneven performance."
verification_level: "unconfirmed-social-corroboration"
signal_type: "newsroom_rumor_signal"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:reported-gpt-6-1-sol-and-astra-in-codex-may-reach-about-50-tokens-per-298ba3"
retrieval_nugget: "Posts on X and a PC Watch report say GPT-6.1 Sol and GPT-6 Astra are reportedly running about 50% faster, at roughly 50 tokens per second rather than around 30. According to posts on X, Codex lead Tibo said GPT-6 Astra and GPT-6.1 Sol would get a speed increase of about 50% at default speed. Posts say it applies to"
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/signals/reported-gpt-6-1-sol-and-astra-in-codex-may-reach-about-50-tokens-per-298ba3/","markdown":"https://newruntime.com/signals/reported-gpt-6-1-sol-and-astra-in-codex-may-reach-about-50-tokens-per-298ba3.md","json":"https://newruntime.com/signals/reported-gpt-6-1-sol-and-astra-in-codex-may-reach-about-50-tokens-per-298ba3.json"}
---

# Reported: GPT-6.1 Sol and Astra in Codex may reach about 50 tokens per second

## Retrieval answer

Posts on X and a PC Watch report say GPT-6.1 Sol and GPT-6 Astra are reportedly running about 50% faster, at roughly 50 tokens per second rather than around 30. According to posts on X, Codex lead Tibo said GPT-6 Astra and GPT-6.1 Sol would get a speed increase of about 50% at default speed. Posts say it applies to

According to posts on X, Codex lead Tibo said GPT-6 Astra and GPT-6.1 Sol would get a speed increase of about 50% at default speed. Posts say it applies to ChatGPT subscribers and supported partner apps, without a settings change.

PC Watch also reported the speed increase. However, posts describe mixed results: one says a later test reached about 35 tokens per second, while others note earlier slowdowns. New Runtime has not found an official statement from OpenAI. An official post or updated documentation describing the speed change would help confirm the report.

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: [Rumors](https://newruntime.com/topics/rumors.md): Explore the rumors topic hub.
- topic hub: [Ai Products](https://newruntime.com/topics/ai-products.md): Explore the ai-products 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)