Caching
Agent loops and long chats send the same history again and again. Zabio marks it for the vendor's cache so you pay the cached rate for it, keeps the cache alive when your turns are slow, and measures your saving with the same cache hits, so the discount is all yours.
The video loads from YouTube only when you press play.
- 75%less per turn on a five-turn Anthropic session with history caching, in our tests
- 1 hourcache picked for you when turns are more than five minutes apart
- 0%of your cache discount taken as our fee
What gets cached
- For Anthropic, your system prompt, your tools and your conversation history, with cache markers Zabio places for you.
- OpenAI, DeepSeek, xAI and Mistral cache on their own. Zabio reports the cached tokens and bills them at the cached rate.
Keeping the cache warm
- A 5 minute cache expires between slow turns and then costs more than no cache at all. When a session's turns are more than five minutes apart, Zabio uses the 1 hour cache instead.
- Within a session, routing keeps a model whose cache is still warm when that is the cheapest honest price.
- Set cache.ttl per call or per key to choose yourself. A value you set always wins.
Your saving, measured fairly
- Your baseline is priced with the same cache hits your call had, so a cache discount never counts as routing's saving.
- Every response shows the cached tokens and what they cost.
- The dashboard shows where your tokens went: history, tool results, cache and reasoning.
Questions
- Does Zabio support prompt caching?
- Yes, on by default where the vendor offers it. For Anthropic, Zabio places cache markers on your system prompt, tools and conversation history, so a long agent loop reads its history from the cache instead of paying for it again on every turn. OpenAI caches automatically. When the turns of a session are more than five minutes apart, Zabio switches to the 1 hour cache so the history is still there. Cached tokens are billed at the vendor's cached rate and shown on every response, and you can set a 5 minute or 1 hour cache per key or per call.
Other features
Smart Splitting
One request, several models, a smaller bill, decided for you on every call. When we can save, we save.
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.
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.