AI Agent StoreNace.AI · Native catalog verified; account access varies
Drex Max Finance
Check financial records against rules and answers you define—for example, whether an invoice exceeds its approved purchase order.
Released 2026-11-01 · First reviewed 2026-11-03 · 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: drex-max-finance. Reads text and up to eight PNG, JPEG or WebP images. Returns yes/no probabilities, choices and ordered scores, not a written analysis. The finance specialization has no independent accuracy or calibration result in this comparison.
Check GET /v1/models with the API key and environment you will use. Send drex-max-finance explicitly; availability can differ by account during rollout. It has its own serving capacity, with no fallback. Omitting the model still selects drex-v2.0.
The 262,144-token limit covers the whole request: shared text, images, all questions and formatting. Each added question consumes that budget. At most 512 questions, 255 options per question, 8 images and 4 MiB serialized input are accepted.
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 ↗