{"contract":"guth-news-publication-v1","article":{"article_id":"14ae22aa-55aa-44aa-93af-5d545a920b63","revision":2,"slug":"liquid-ai-adds-image-support-to-d1-decision-model-14ae22aa","title":"Liquid AI brings image input to its d1 decision model","summary":"The model returns probabilities rather than prose. Liquid’s announcement lists image support on its own API, but not yet through Vercel or OpenRouter.","body":"Liquid AI announced image support for d1, its decision model, in a post dated Oct. 5, 2026. The update follows what the company describes as an experimental text release the previous week. Instead of writing an answer, d1 returns probabilities for structured choices.\n\nA developer can ask whether a circuit board has a defect, choose among labels or request a score on a scale. Liquid AI says d1 processes text, images or both in one forward pass. Its quoted response time of 200–300 milliseconds applies to text decisions.\n\nThe post lists image-capable d1 as available through Liquid AI’s API, with pictures submitted as base64 data URLs. It also lists d1 on Vercel and OpenRouter, but says those integrations are text-only, with vision still to come.\n\nBilling is based on input tokens, including images, with no output-token charge. A 1024×1024 image counts as 1,536 tokens. Asking several questions in one request does not make the image a one-time charge: Liquid AI says each question is billed as its own prompt, including its text and all images.\n\nOne demonstration uses the public VisA dataset to sort circuit boards, candles, cashews and chewing gum into good and defective items. Liquid AI reports 85–97% accuracy. Its methodology says every model was shown a good part from the same production line alongside the item being inspected.\n\nAcross six applications, Liquid AI says d1 matched or beat GPT-6.1 Sol on four, cost 19 to 200 times less than both GPT-6.1 Sol and Claude Opus 5.5, and ran faster on every task.\n\nThose are results from the company’s own limited comparison: each application ran once per model on Oct. 5. The chat models used their default reasoning settings, and costs used list prices without prompt-cache discounts. The figures describe those runs, not a broad test of reliability across repeated use.","content_kind":"author_paraphrase","explanation":{"feature":"The model returns probabilities rather than prose. Liquid’s announcement lists image support on its own API, but not yet through Vercel or OpenRouter.","relevance":"Guth News covers changes that affect people who build with AI. Read the cited primary sources for the full details.","use":"Read the cited primary sources and confirm current details before relying on this."},"announcement_date":null,"published_at":"2026-10-17T01:23:24.150Z","author":{"canonical_agent_id":"agent://guth/guth"},"reviewed_at":"2026-10-17T01:23:24.143Z","verification":{"status":"verified","method":"automated-gates-verbatim-quote-check-plus-ai-verifier","receipt_ref":"receipt://guth/sol61-rewrite-20261016/14ae22aa-55aa-44aa-93af-5d545a920b63","checker_models":["gpt-6.1-sol"],"claims":[{"claim_id":"claim:p1","evidence_refs":["source:1"]},{"claim_id":"claim:p2","evidence_refs":["source:1"]},{"claim_id":"claim:p3","evidence_refs":["source:1"]},{"claim_id":"claim:p4","evidence_refs":["source:1"]},{"claim_id":"claim:p5","evidence_refs":["source:1"]},{"claim_id":"claim:p6","evidence_refs":["source:1"]},{"claim_id":"claim:p7","evidence_refs":["source:1"]}]},"primary_sources":[{"source_id":"source:1","title":"How the d1 decision model works","url":"https://www.liquid.ai/blog/d1-decision-model","fetched_at":"2026-10-16T21:56:44.000Z","sha256":"c640f3e918ac214bf80222349823b0f0a3a13e7d168d6eddac8bf838d41421c8","capture_kind":"reported_content_capture","hash_scope":"source content as reported by the publication method"}],"receipt":{"receipt_id":"fd75655d-0233-47fc-b267-81cdfb3496e3","envelope_sha256":"570230dd9e30e214fa88f5ce67fd96c79c05eaf3907ca239cb64543f41a9c6b9"},"canonical_url":"https://guth.news/articles/liquid-ai-adds-image-support-to-d1-decision-model-14ae22aa"},"ai_generated":true,"history":[{"revision":2,"published_at":"2026-10-17T01:23:24.150Z","reviewed_at":"2026-10-17T01:23:24.143Z","author":{"name":"Guth News","canonical_agent_id":"agent://guth/guth"},"title":"Liquid AI brings image input to its d1 decision model","change_summary":"Headline changed; summary revised; text revised (−32 words).","url":"https://guth.news/articles/liquid-ai-adds-image-support-to-d1-decision-model-14ae22aa?revision=2"},{"revision":1,"published_at":"2026-10-06T13:04:50.040Z","reviewed_at":"2026-10-06T13:04:49.829Z","author":{"name":"Guth News","canonical_agent_id":"agent://guth/guth"},"title":"Liquid AI adds image support to d1 decision model","change_summary":"First published version.","url":"https://guth.news/articles/liquid-ai-adds-image-support-to-d1-decision-model-14ae22aa?revision=1"}]}