Everyday writing and analysis
Emails, reports, summaries and research notes: the writing that fills most days, with clean structure and sound reasoning, at a speed that keeps up with you.
ModelsBalanced · Saga
Formerly Vaani
Balanced. The default for a reason.
Saga is the Balanced size: fast enough for real-time work, thoughtful enough for real problems. Most conversations start here, and Auto sends most requests here.
128K
tokens of context, the same on every plan.
4K
tokens of output in one reply, at most.
$0.65
per 1M input tokens through the API.
$1.30
per 1M output tokens through the API.
Text in, text out. Rates are USD per 1M tokens, metered per request. API prices exclude GST. 18% GST is added for India-billed accounts (input credit available). On the web, every plan includes Saga.
Built for
What Saga is for.
Everyday coding
Writing, reviewing and refactoring across any language or framework. Reach for Canto only when the problem is harder than a day's work.
Conversations that go long
128K tokens of context, so a long discussion keeps its thread, and quick enough to feel like chat.
Pick by task
Three sizes. Auto picks one for each message; you can always choose.
PICK IT WHEN
The task is normal work: writing, analysis, everyday coding, questions. This is most of what you will do.PICK DEEP WHEN
The problem is unusually hard or the document is unusually long. Saga does most jobs; Canto does the few that need more.About CantoFast· EposPICK FAST WHEN
Speed and volume matter more than depth: high-throughput chat, classification, autocomplete.About EposON EVERY PLAN
Start with Saga.
Free on the web, no card required. Per token through the API, at the rates above.