Simple, Transparent Pricing

How is token-based billing different from subscriptions?

With tokens, you only pay for actual API usage - no monthly fees, no wasted credits. You get charged per query based on actual tokens used, not a fixed monthly rate - industry-standard pay-as-you-go pricing.

What's included in every API response?

Every response includes: (1) Detailed token usage (input/output/cached), (2) Complete cost breakdown (Astro Engine + AI processing), (3) Wallet balance (before/after), (4) Full pricing transparency.

How does prompt caching work?

When you query the same birth details multiple times, Vedika caches the astronomical calculations. Subsequent queries use cached data, reducing costs by 90% automatically - no configuration needed.

What if I run out of credits?

You'll receive a 402 Payment Required response with your balance deficit clearly shown. Simply add more credits to your wallet via the dashboard and continue using the API immediately.

How accurate is the pricing calculator?

Our calculator shows typical ranges. Actual costs may vary by ±15% based on query complexity, number of agents activated, and astronomical data requirements. All costs are shown in your API response metadata.

Is streaming available? Does streaming cost extra?

Yes! Server-Sent Events (SSE) streaming is available at /api/v1/astrology/query/stream and /api/vedika/chat/stream endpoints. Get real-time responses as agents process your query, improving perceived performance by 60%.

Billing: Streaming endpoints use identical token-based billing as non-streaming endpoints. You'll receive a billing_completed SSE event after streaming finishes, showing exact cost, wallet balance (before/after), and complete token breakdown.

No premium: Streaming costs the same as non-streaming. The final billing_completed event provides full transparency - same pricing, better UX.