Frequently Asked Questions

Vedika is a first-party indic-native astrology LLM — not a wrapper over generic chat models. It's purpose-built on the classical Vedic corpus (BPHS, Phaladeepika, Saravali) and combined with Vedika Ephemeris for sub-arcsecond astronomical precision. 140+ calculation endpoints plus two AI delivery paths: Normal path (full deep analysis in 20-30s, all plans) and Fast path (same depth in 1-3 seconds, Business $120+). Built in India. No data leaves India.

Yes! Vedika offers a FREE Sandbox environment at api.vedika.io/sandbox/* with realistic mock data. Build your entire integration without spending a dime - no credit card required. When ready for production with real astronomical data, plans start at just $12/month with wallet credits for any endpoint.

Vedika AI has an 82% accuracy match rate with professional astrologers, compared to ~51% for general-purpose AI chatbots. We use Vedika Ephemeris for astronomical calculations (NASA-grade precision) combined with AI trained on over 10,000 real astrology consultations.

Vedika supports 30 languages including English, Hindi, Tamil, Telugu, Bengali, Gujarati, Kannada, Malayalam, Marathi, Punjabi, Odia, Assamese, Sanskrit, Nepali, Urdu, and more. You can request responses in any of these languages via API parameters.

Unlike general-purpose AI chatbots which use generic knowledge without precise calculations, Vedika performs actual astronomical calculations using Vedika Ephemeris to determine exact planetary positions, then applies AI trained specifically on Vedic astrology principles. General AI chatbots cannot calculate planetary positions accurately, while Vedika provides astronomical-grade precision combined with astrological expertise.

Depends on which path you use. Calculation endpoints (birth chart, dasha, panchang) respond in under 200ms. AI queries come in two speeds: Normal path runs at 120 tokens/second and delivers a full deep analysis in 20-30 seconds (available on all plans from $12). Fast path runs at 1,800 tokens/second and delivers the SAME depth in 1-3 seconds (Business $120 + Enterprise $240 only). We guarantee 99.9% uptime with dual-region India + US failover.

Fast path is Vedika's 1-3 second AI delivery tier. It runs the same complete Vedic analysis as the normal path — same chart calculations, same dashas, same yogas, same remedies, same depth — but streams the answer 10-15× faster (1,800 tokens/sec vs 120). There is no quality trade-off. Fast path handles large multi-paragraph outputs at speed, ideal for consumer-facing chat UX, voice AI, and live support. Available on Business ($120/mo) and Enterprise ($240/mo) plans at $0.02-$0.05 per query.

Yes, on Business ($120/mo) and Enterprise ($240/mo) plans. Endpoints: POST /api/v1/voice (blocking) and POST /api/v1/voice/stream (SSE streaming). Three tiers: vedika-voice-cheap for budget Hindi, vedika-voice-premium for multilingual high-quality, vedika-voice-jarvis for ultra-low-latency conversational UX. All tiers run on top of the same deep Vedic analysis. Billed on your wallet.

Yes, Enterprise customers get a dedicated Vedika instance deployed in your preferred GCP region (Mumbai, Frankfurt, Singapore, US, etc.). Your data never leaves your chosen region. Fully managed by Vedika — no infrastructure work on your end. Starting at $1,999/month.

Vedika offers 140+ calculations including: Birth Charts (D1-D60 divisional charts), Vimshottari Dasha (planetary periods), Ashtakoota Compatibility (36 Guna matching), Yogas (300+ combinations), Transits, Muhurtha (auspicious timing), Numerology (37 types), Panchang, and AI Chatbot Queries. Full documentation available at https://vedika.io/docs

Integration is simple: 1) Sign up at https://vedika.io/console to get your API key (format: vk_live_*). 2) Make POST requests to https://api.vedika.io/api/v1/astrology/query with your API key in the Authorization: Bearer header. 3) Send a question and birth details in JSON format. We provide SDKs for JavaScript and Python, plus an MCP server for AI agents.

Yes! Vedika now offers comprehensive Western (tropical zodiac) astrology support via our /v2/western/* endpoints. Available features include transit charts, secondary progressions, solar returns, synastry for relationships, composite charts, and daily horoscopes. All calculations use Vedika Ephemeris with tropical zodiac precision. Pricing starts at $0.048/call for horoscopes, up to $0.148/call for relationship analysis. View Western astrology documentation.

Vedika guarantees 99.9% uptime SLA. We use a 3-tier fallback system: primary ephemeris server, backup ephemeris server, and cached planetary data. Our infrastructure is distributed across multiple regions with automatic failover. Real-time status available at https://vedika.io/status

Pricing: FREE Sandbox for development (unlimited mock data, no credit card). Production plans: Starter $12/month (normal-path AI, 1,000 calls), Pro $60/month (10,000 calls, higher rate limits), Business $120/month (+ Fast Path 1-3s reply + Voice AI), Enterprise $240/month (everything + wallet top-up). Wallet-based billing. Per-query cost: $0.01-$0.03 normal path, $0.02-$0.05 fast path (same deep analysis, delivered in 1-3 seconds). All plans include 140+ endpoints and MCP server.

Yes, absolutely. Vedika is designed for commercial B2B use. Our clients include horoscope apps, matrimony platforms, wellness apps, media companies, and chatbot developers. All paid plans include commercial usage rights. Enterprise plans offer white-labeling options.

Prokerala offers traditional astrology calculations only, while Vedika adds AI chatbot capabilities on top of traditional calculations. Vedika's unique feature is natural language understanding - you can ask "What career suits me?" instead of manually interpreting planetary positions. Vedika also offers more endpoints (100+ vs ~80) and better language support (30 languages vs English only).

Support is available via: Email ([email protected]), Documentation (https://vedika.io/docs), API Reference (https://vedika.io/api-reference), and Status Page (https://vedika.io/status). Paid plans include priority email support with 24-hour response time. Enterprise plans include dedicated support with <1 hour response for critical issues.