{"slug": "plaid-speed", "title": "Plaid Speed", "summary": "Amp added a \"Plaid\" speed tier for modes using GPT-6 Astra, running inference requests up to 6× faster than normal requests at 6× the cost per token. The tier is selected in the new thread dialog's mode picker by moving the speed switch past Fast to Plaid, and works with both Amp-provided inference and linked ChatGPT subscriptions that support ultrafast. When Plaid is active, subagents and non-Plaid-enabled model inference fall back to fast and then standard speed.", "body_md": "Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid inference requests run up to 6× faster than normal requests and cost 6× as much per token.\n\nOpen 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**.\n\nPlaid works with both Amp-provided inference and linked ChatGPT subscriptions that support ultrafast. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast and then standard speed.", "url": "https://wpnews.pro/news/plaid-speed", "canonical_source": "https://ampcode.com/news/plaid-mode", "published_at": "2026-09-29 00:00:00+00:00", "updated_at": "2026-09-29 20:49:44.500306+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "large-language-models", "ai-infrastructure"], "entities": ["Amp", "Plaid", "GPT-6 Astra", "ChatGPT"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/plaid-speed", "markdown": "https://wpnews.pro/news/plaid-speed.md", "text": "https://wpnews.pro/news/plaid-speed.txt", "jsonld": "https://wpnews.pro/news/plaid-speed.jsonld"}}