---
title: Plaid Speed
link: https://ampcode.com/news/plaid-mode
source: ampcode-com
published: 2026-09-29T00:00:00Z
updated: 2026-09-29T00:00:00Z
first_seen: 2026-10-03T23:09:50.514863041Z
summary: Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token. Open the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past Fast to Plaid. Plaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.
content: extracted
html: 2026-09-29-plaid-speed.html
preview:
  file: 2026-09-29-plaid-speed.preview-389cb62203a5.webp
  width: 256
  height: 134
  color: '#81796d'
images:
- source: https://ampcode.com/og?_template=news&_version=7&title=Plaid+Speed&date=September+29%2C+2026&tagline=6x+faster+inference+for+GPT-6+Astra&screenshot=https%3A%2F%2Fstatic.ampcode.com%2Fnews%2Fplaid-new-thread-toggle-6x-final-20260929.avif&sig=0cf79ab81ddd72b0858526e348ae84f4300119d85e54838a77975465b466c750
  original:
    file: 2026-09-29-plaid-speed.image-6212117a76a8.png
    width: 1200
    height: 630
  variants:
  - file: 2026-09-29-plaid-speed.image-dd643683f206.webp
    width: 320
    height: 168
  - file: 2026-09-29-plaid-speed.image-3dd5cfb50cec.webp
    width: 640
    height: 336
  - file: 2026-09-29-plaid-speed.image-797179963bd2.webp
    width: 960
    height: 504
  - file: 2026-09-29-plaid-speed.image-edfb21df948e.webp
    width: 1200
    height: 630
  color: '#625d57'
- source: https://static.ampcode.com/news/plaid-new-thread-toggle-6x-final-20260929.avif
  original:
    file: 2026-09-29-plaid-speed.image-eeb0f121703c.avif
    width: 1664
    height: 1324
  color: '#7a7a7e'
---

Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token.

Open the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past **Fast** to **Plaid**.

![The mode dial with high selected and the speed switch set to Plaid, showing the red 6× cost indicator](https://static.ampcode.com/news/plaid-new-thread-toggle-6x-final-20260929.avif)

Plaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.