{"data":{"slug":"amd-mi400","etype":"chip","name":"AMD Instinct MI400 / MI450","cat":"GPU","subtitle":"AMD's 2026 rack-scale answer — and the chip behind the OpenAI 6-gigawatt deal.","summary":"The MI400 series, announced for 2026, targets 432 GB of HBM4 and roughly 40 PFLOPS of FP4 per GPU, shipping in the 72-GPU 'Helios' rack platform. In October 2025 OpenAI and AMD announced a multi-year agreement to deploy up to 6 gigawatts of Instinct GPUs beginning with MI450 in late 2026 — with an equity warrant structure — the strongest customer endorsement AMD's AI line has received. All figures are announced targets.","attrs":[{"g":"Overview","l":"Designer","v":"AMD"},{"g":"Overview","l":"Status","v":"Announced for 2026"},{"b":"Vendor claim","g":"Memory","l":"Memory (announced)","v":"432 GB HBM4, ~19.6 TB/s"},{"b":"Vendor claim","g":"Compute","l":"FP4 (announced)","u":"PFLOPS","v":"~40"},{"b":"Vendor claim","g":"Physical","l":"Platform","v":"Helios rack — 72 GPUs, doubling as AMD's NVL72 answer"},{"b":"Reported","g":"Overview","l":"Flagship commitment","v":"OpenAI: up to 6 GW of Instinct deployment starting with MI450 in 2H 2026"}],"kf":{"year":2026,"class":"GPU","memory":"432 GB HBM4","designer":"AMD"},"aliases":["MI400","MI450","Helios"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":"Ramping","region":null,"asof":"2026-08-31","sources":[{"url":"https://www.amd.com/en/newsroom/press-releases/2025-10-6-amd-and-openai-announce-strategic-partnership-to-d.html","label":"AMD–OpenAI announcement (Oct 2025)"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T03:45:15+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}