Smart Splitting
One request, several models, a smaller bill. When a request carries a long document and asks about part of it, Zabio has a cheap model copy out the lines that matter, checks nothing is missing, and lets the model auto picked answer from the excerpt. When we can save, we save. When we can't, nothing changes.
The video loads from YouTube only when you press play.
- 35%cheaper on long-document questions, on average in our tests
- 57 to 66%cheaper on questions about contracts, in our tests
- 30 of 30split answers kept every planted fact
- 0 USDextra for you when a split falls back: the attempt is on us
How it works
1. Is it worth a look?
After routing picks the model, Zabio estimates what the call would cost unsplit. Cheap calls stop here and run as usual.
2. Can it be split?
For calls expensive enough, one quick question to Jev asks whether the request carries a large source and a question that needs only part of it. We pay for that question, never you.
3. Is it cheaper?
Zabio prices both paths, including any warm cache a split would lose, and splits only when the split is clearly cheaper.
4. Extract, word for word
A cheap model copies out the lines the question needs, exactly as written, never a summary, so the answering model sees real evidence.
5. Check
Jev checks that the extract holds everything the question needs. If it does not, the full document goes to the chosen model and we pay for the attempt.
6. Answer
The model auto picked answers from the excerpt, told that the source was excerpted and that it can ask for more.
When it applies
- Under auto only, on any line. A model you name is never split.
- Long material with a narrow question: contracts, policies, manuals, long support threads, batches of reviews.
- Not when the job needs every word, such as translating or proofreading a whole document.
- Not when routing already picked a cheap model, since then there is nothing to save.
Your guarantees
- A split never costs you more than the unsplit call: a failed attempt is our cost.
- Every step shows in zabio.split: the extract, the check, each model and what it cost.
- Turn it off for any request with zabio.split set to off, or the header x-zabio-split: off.
- One request, one fixed fee for automatic model choice: the extract and the answer are billed at list price plus the service fee, and every cent the split saves is yours.
Questions
- What is Smart Splitting?
- Under auto, a request that carries a long document and asks about only part of it can be split: a cheap model copies out the lines the question needs, word for word, Jev checks that the extract holds everything the answer needs, and the model auto picked answers from that extract instead of the whole document. If the check fails, Zabio sends the full document and pays for the attempt itself, so a split never costs you more. In our tests it cut the cost of long-document questions by about a third on average, and by more than half on contracts, with every fact kept. It never applies to a model you name, every step shows in zabio.split, and zabio.split set to off turns it off for a request.
- How is Zabio different from other AI routers?
- It picks the model for you, to get you more right answers for less. Send auto and Zabio reads each request, picks the model and reasoning setting that fit the job, and shows why on every response, with what the call cost and what it saved. Pricing stays simple: the provider's list price, a small service fee on each call and a small fixed fee on each auto request. Zabio takes no cut of what routing saves, so every cent of the saving is yours.
Other features
Smart routing
The right model and reasoning setting for every request, picked from evidence, with the reason on every response.
Jev for classification
Tagging, routing, moderation and sentiment for a fraction of the price of a chat model, named or picked by auto.
Caching
Your history cached for you, the 1 hour cache when turns are slow, and never a cut of your cache discount.
Flex
Half price when you can wait, with one deadline field.
Batching
Thousands of requests in one file at about half price, with auto routing on every line.
Teams and keys
Organizations, member quotas, keys with spend caps and model lists, and your own vendor keys with no service fee.
Start free, upgrade when it's real
Change two lines in your code, send model auto, and every response shows what it cost and what you saved.