Sub-400ms responses, high-volume throughput, and pricing that works at scale. Mira is the model for the moments where latency matters more than depth.
Capabilities
Sub-400ms to first token means Mira feels instant. Build chatbots, support agents, and conversational interfaces where any perceptible lag breaks the experience.
Tagging, routing, moderation, sentiment, intent - Mira handles the small decisions that happen millions of times a day. At ₹13 per million input tokens, running Mira at scale stays affordable.
Fast enough to live inside an editor or search box, Mira powers the inline AI experiences where response time is the product.
Pricing
Input
For prompts at real-time-chat volume. $0.15 per 1M in USD.
Output
For generated responses, at any volume. $0.80 per 1M in USD.
At these prices, a million user messages costs less than a cup of chai.
Choose well
Pick Mira when speed and cost are the product - real-time chat, classification, autocomplete, anything that happens thousands of times per minute.
Pick Vaani when you need reasoning quality or vision, and the workload isn't latency-critical. Most interactive apps fit Vaani, not Mira.
Pick Kavi when the task is rare, hard, and accuracy-critical.