PsyCortex.
India's 400B+ multimodal AI engine.
Built in Bharat by Dr. Nitnem Singh Sodhi at Bharat NeuroTech. 400+ billion parameters, 20+ billion active per token, on our proprietary sparse attention technology — and India's only AI model that understands human psychology. Natively across text, vision, audio and documents. The same engine powers the Lab chat, the ₹1,799 AI Audit, the consult prep notes, and every Custom AI Deployment we ship.
One engine, one INR wallet. PsyCortex runs every chat surface on the site — and plugs into any MCP-compatible client via /mcp.
What's under the hood.
| Engine | PsyCortex · by Bharat NeuroTech |
| Parameters | 400+ billion (proprietary sparse attention, 20+ billion active per token) |
| Context window | Infinite Context Window · up to 100B tokens/request (enterprise) |
| Modalities | Text · Vision · Audio · Documents (PDF/DOCX) · Short video |
| Reasoning | Standard · PsyReason (Deep Thinking) · PsyAgent (tool-use) |
| Inference | INR-billed, paise-metered |
| Data handling | DPDP-aligned, audit-trail, session-only specs |
| API surface | OpenAI-compatible REST · Bearer auth · per-key daily caps |
| SLAs | Upstream timeouts: 60s non-stream · 120s stream · auto-refund on failure |
Backend infrastructure is proprietary. What we publish is capability, architecture class, price and audit trail — the engine identity, prompting, tool-runtime, audit trail and billing are all ours.
One engine for every job.
Chat, decoding and native image understanding. 20+ billion active parameters per token keep latency chat-grade across Human Intelligence, Business Intelligence and everyday audit chat.
The same 400B+ engine handles long-horizon planning, agentic tool-use, code synthesis, emotional intelligence and human psychology. PsyCortex replaced NeuroCortex and EQCortex in August 2026 — no model picking, no wrong choice.
One engine, four modalities.
Long-form drafting, summarisation, code, policy analysis. Toggle Deep Thinking Mode to reason privately and return only a clean, defensible answer.
Upload photos, screenshots, diagrams or scanned documents. PsyCortex reads them inline and reasons over them in the same turn.
Voice notes, calls and meetings — transcribed, then audited for language and delivery signals via /api/psycortex/listen.
PDFs and DOCX up to the Infinite Context window. Powers the ₹1,799 AI Audit chatbot and the consult prep workflow.
India's only AI engine with a virtually infinite context window.
Powered by PsyMemory — the Memory layer of Dr. Sodhi's Software Neurotechnology paper (IndJCST 2026, DOI 10.59256/indjcst.20260502087). Open access. Read the paper →
PsyCortex ships an infinite context window — Software Neurotechnology (PsyMemory) scales the native window to virtually infinite. Tier ceilings per request:
| Surface | Ceiling per request |
|---|---|
| Free trial (no signup) | 1M tokens |
| Signed-in chat | 10B tokens |
| Public API | 25B tokens |
| Enterprise / custom deployment | Up to virtually infinite |
Inputs up to ~32K tokens are included in the base ₹0.50/msg. Larger inputs pay a size-banded Extended context surcharge — see Pricing. PsyMemory is proprietary; implementation is closed, capability is not.
Paise, not pennies.
One INR wallet for every surface. API calls debit the same wallet at a tier multiplier — see /api/docs.
12 standards. Flat fee per guided run. ISO 42001/27001/27701 lead-auditor upgrade.
One hour, PsyCortex on screen, written decision map + 24-hr async follow-up.
The peer-reviewed 20-layer framework PsyCortex ships (Sodhi, IndJCST 2026).