AI Agent StoreNace.AI · Native model verified
Drex Max
Check text and images against up to 512 questions—for example, identify a damaged parcel and choose how to handle the claim.
Released 2026-10-13 · First reviewed 2026-10-20 · Checked 2026-11-03. The provider’s model table dates this version October 13; first verified in this comparison October 20.
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: drex-max. Reads text and images and returns probabilities for choices, yes/no questions and ratings. Up to 512 questions are allowed; that limit does not guarantee completion within the service timeout.
Select drex-max explicitly. The drex-latest alias and omitted model still choose v2.0. Larger accepted requests can time out; fewer questions may be needed for long inputs. Check the available-model list with your actual API key; availability can differ by environment.
Original Drex Max permits up to 512 questions, 255 options per question and 8 images. Its 262,144-token limit applies to shared information plus each question; long questions also share an aggregate budget. It can shorten long state before inference. Version v1.1 instead counts all questions in one whole-request token budget.
Output: Yes/no probabilities, choices and ordered scores; no written explanation. Compare decision models, limits and input costs ↗
Costs $0.03 per million billed input tokens, including image tokens. Output and failed requests are not charged. Use the successful response’s input usage to calculate the bill. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
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 ↗