{"rewrite":{"id":"r_5db07267ff741fff6c2c231a","clusterId":"c_9a34122c3c72c46691fc5dd6","slug":"liquid-ai-gives-d1-image-input-matching-gpt-6-1-sol-at-lower-cost","model":"deepseek-v4-1-flash","headline":"Liquid AI Gives d1 Image Input, Matching GPT-6.1 Sol At Lower Cost","summary":"Liquid AI's decision model d1 now accepts images as well as text or both at once, the company said. Tested against GPT-6.1 Sol and Claude Opus 5.5 on six applications, from filtering support tickets to inspecting circuit boards, d1 matched or beat GPT-6.1 Sol on four, ran at 19 to 200 times lower cost, and answered faster on every task, at 200 to 300 ms for text.","whyItMatters":"A model that answers in a single forward pass without generating tokens sidesteps the cost structure of generative systems, so matching a frontier model on four of six tasks at a fraction of the price is the opening bid in a different kind of comparison than benchmark leaderboards use.","webCardHtml":"\u003cp\u003ed1 does not write out answers. It returns the probability of each option in one forward pass, which is why text decisions land in 200 to 300 milliseconds and why image input is a cheap addition: the same pass now reads pixels or prose. Liquid AI says the model was tested on six real applications, from support ticket filtering to circuit board inspection, against GPT-6.1 Sol and Claude Opus 5.5.\u003c/p\u003e\u003cp\u003eOn demos, d1 classified good and defective parts at 85 to 97 percent accuracy without training, read a Wordle board straight from a screenshot so developers no longer needed a text version, and guessed drawings in Quick, Draw! at an average of 5.2 out of 6.\u003c/p\u003e","blueskyPost":"Liquid AI's d1 decision model now takes images as well as text. On six test applications it matched or beat GPT-6.1 Sol on four, at 19x to 200x lower cost and faster on every task. Text decisions run 200 to 300 ms because it returns probabilities in one forward pass.","twitterPost":"Liquid AI added image input to its d1 decision model. Tested on six applications against GPT-6.1 Sol and Claude Opus 5.5, d1 matched or beat GPT-6.1 Sol on four, cost 19x to 200x less, and answered faster on every task. Text decisions take 200 to 300 ms.","threadsPost":null,"newsletterBlurb":"Liquid AI's decision model d1 now accepts images, text, or both as input. In tests across six applications, from support ticket filtering to circuit board inspection, d1 matched or beat GPT-6.1 Sol on four and ran at 19 to 200 times lower cost than both it and Claude Opus 5.5, with faster responses on every task. The model answers with probabilities in one forward pass rather than generating tokens.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20261008-d1-with-vision/\",\"title\":\"Decision-Making Model \\\"d1\\\" Now Supports Image Input, Beating GPT-6.1 Sol on the Same Tasks with Higher Accuracy, Speed, and Lower Cost\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4684,"outputTokens":703,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1791413604,"createdAt":"2026-10-07T22:47:52.000Z","publishedAt":"2026-10-07T22:51:08.000Z","updatedAt":"2026-10-07T22:51:08.000Z"},"cluster":{"id":"c_9a34122c3c72c46691fc5dd6","canonicalTitle":"意思決定モデル「d1」が画像入力に対応、同一タスクでGPT-6.1 Solより高精度・高速・低コスト","representativeArticleId":"a_e9e01468759fd45008f720a8","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"d1\"],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-10-07T22:00:00.000Z","lastSeenAt":"2026-10-07T22:00:00.000Z","updatedAt":"2026-10-07T22:51:08.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20261008-d1-with-vision/","title":"意思決定モデル「d1」が画像入力に対応、同一タスクでGPT-6.1 Solより高精度・高速・低コスト"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["d1"],"studios":[],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":null}