AI Agent StoreLiquid AI · Provider documented
Liquid d1-ultra
Check a photo against a damage claim, inspect a component or route a difficult support case. Supply the possible answers; the model returns probabilities rather than writing a reply.
Released 2026-10-15 · First reviewed 2026-10-16 · Checked 2026-11-03.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: d1-ultra. Accepts text and images for yes/no, choice and score questions. The launch compares it with d1 and Jev, but those are the developer’s tests, not independent measurements in this ranking.
Use d1-ultra with Liquid’s decision endpoint. Gateway also lists a separate offer; check that service’s limits and billing before switching.
Native context and question limits are not yet verified. Gateway separately lists liquid/d1-ultra at 32,768 tokens; that does not establish the direct API limit.
Output: Yes/no probabilities, choices and ordered scores. Compare decision models, limits and input costs ↗
Each question is billed as its own prompt, including all images. A 1024×1024 image counts as 1,536 input tokens per question. Use the sum of billed tokens across questions in the calculator. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Check whether confidence scores match the answers you can verify.
Compare caching and long-context costs ↗