One OpenAI-compatible endpoint, a prepaid ₹ balance, scoped keys and per-token billing — everything you need to go from key to production.
Every model under one sky.
India's prepaid LLM API marketplace. One API key to Llama, Mistral, Qwen and 13 more open models. OpenAI-compatible endpoints. Pay in rupees via UPI, RuPay, or net banking. No forex markup, no forced subscription, no international credit card required.
Tokens start moving before the route settles. No buffering, no faux typing.
Chat, code, embeddings, vision, speech and reasoning behind one key.
Load via UPI, cards, or net banking. Purchased credits never expire.
The catalog. Noctilucent clouds included.
Sixteen open models behind one endpoint. Same request shape everywhere — swap a model string, nothing else moves.
Real clouds stay in the troposphere. Around 75 km you are in the mesosphere, where noctilucent clouds can appear at night.
Mistral 7B Instruct
Mistral AIMultilingual
Fast, multilingual 7B model ideal for chat, text generation, and classification. Available on every plan with ₹0.02/1K tokens.
Qwen3.6 27B
AlibabaChat · Function Calling
Alibaba's 27B model with 128K context. Supports chat and function calling at competitive pricing.
Qwen3 Coder 30B
AlibabaCode
Alibaba's 30B code-specialised model with 128K context. Excellent for code generation, debugging, and technical tasks at ₹0.01/1K input.
Llama 3.3 70B Instruct
MetaMultilingual
Meta's flagship 70B model with 128K context. Top-tier multilingual performance for complex chat, analysis, and generation tasks.
GPT OSS 120B
OpenAIReasoning
OpenAI's 120B open-source reasoning model. Exceptional depth for complex problem-solving. Requires Pro plan or above.
Qwen3.5 397B
AlibabaChat · Function Calling
Alibaba's 397B MoE model with 256K context. Massive capacity for complex chat and function calling. Pro plan required.
BGE M3
BAAIMultilingual
BAAI's M3 embedding model supporting dense and sparse retrieval. Excellent for multilingual RAG pipelines at ₹0.01/1K tokens.
Built like a product, not a reseller page.
Everything between your code and the GPU is ours to obsess over — billing in paise, streaming that actually streams, keys you can rotate without downtime.
A Prepaid Balance, Not a Credit Card Trap
Prepaid — like your phone. Load it over UPI, watch every request debit in paise, and credits never expire.
Streaming That Streams
Tokens leave our gateway the instant the model emits them. No buffering theatre — we removed every hop that held bytes hostage.
Real SSE streaming, chunk-by-chunk
One Line to Migrate
OpenAI-compatible surface. Point your existing SDK at us and ship.
Built for India
Prepaid ₹ balance, UPI top-ups, billed for Indian teams.
🇮🇳The boring parts are designed.
Billing, access, retention and audit trails sit beside the model catalog, not behind it.
Processed, Not Mined
Prompts and completions are processed to deliver your request, bill usage, and prevent abuse — per the privacy policy.
GST Invoices
Balance top-ups stay clean for Indian finance teams and procurement flows.
Scoped Keys
IP allowlists, expiry windows and rotation flows are first-class console controls.
DPDP-Ready Posture
Export, retention and deletion workflows are planned into the product surface.
Every operational promise on the landing page maps to a console screen in the product mockup.
Five minutes to first token.
If you've used the OpenAI SDK, you already know our API. Same shapes, same streaming, same errors — different bill.
Sign Up, Get ₹50
Email or Google. Credits land before your coffee brews.
Mint a Key
nbh_… — scope it, allowlist it, or don't. Your call.
Swap the Base URL
Responses carry X-Cost-INR so finance stops asking.
from openai import OpenAI client = OpenAI( base_url="https://api.nabh.cloud/v1", api_key="nbh_...", # that's the whole migration ) stream = client.chat.completions.create( model="llama-3-70b-instruct", messages=[{"role": "user", "content": "नमस्ते!"}], stream=True, ) for chunk in stream: print(chunk.choices[0].delta.content or "", end="")
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.nabh.cloud/v1", apiKey: process.env.NABH_API_KEY, }); const stream = await client.chat.completions.create({ model: "llama-3-70b-instruct", messages: [{ role: "user", content: "नमस्ते!" }], stream: true, }); for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
curl https://api.nabh.cloud/v1/chat/completions \ -H "Authorization: Bearer $NABH_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "llama-3-70b-instruct", "stream": true, "messages": [{ "role": "user", "content": "नमस्ते!" }] }' # data: {"delta":{"content":"नमस्ते"}} ← arrives immediately # data: {"delta":{"content":"!"}} ← and keeps arriving
Prepaid. Like your phone.
Tokens cost the same on every plan — plans only raise your ceilings. Load your balance, spend it down, top up when you like.
Free
Start exploring
- ₹50 free credits on signup
- Access: Mistral 7B Instruct (free tier)
- 5 requests / min rate limit
- 500 requests / day
- 1 API key
- Community Discord support
Developer
Pay as you go
- Access to 13 developer-tier models
- 60 requests / min rate limit
- 10,000 requests / day
- 5 API keys
- 30-day analytics history
- Email support
- Recharge via UPI / RuPay / Cards
Pro
For teams & scale
- Priority queue access
- Access to Pro-only models (120B, 397B, Vision)
- Unlimited daily requests
- 50 API keys
- 12-month analytics history
- Priority email support + Slack
- Team seat management
- Custom recharge limits
Enterprise
For teams with a compliance officer.
- Dedicated capacity
- DPDP agreements
- Custom rate limits
- Slack channel, real humans
Fair questions.
Do my prepaid credits expire? +
Purchased credits — never. The monthly ₹50 free credits reset on the 1st; whatever you loaded yourself stays until you spend it.
Is this really OpenAI-compatible? +
Request and response shapes, streaming format, and error codes follow the OpenAI spec. Existing SDKs work by changing base_url and the key. If something behaves differently, that's a bug — tell us.
Do prices include GST? +
Balance top-ups are billed with GST at checkout and you get a proper invoice. Per-token rates shown are what leaves your balance — no surprise line items.
Is my data used for training? +
Your prompts and completions are processed only to serve your request, bill usage, and prevent abuse. See our Privacy Policy for how data is handled.
Which payment methods work? +
Any UPI app (GPay, PhonePe, Paytm), cards, and netbanking via Razorpay. Enterprise can pay by invoice.
Welcome to nabh.cloud
The sky isn't the limit. It's the product.
₹50 of credits are waiting. Billing is per token, in paise. See you up here.
