Documentation

nabh.cloud API

One OpenAI-compatible API for open large language models — billed per token in Indian Rupees from a prepaid wallet.

The nabh.cloud API gives you an OpenAI-compatible endpoint for a catalogue of open models (text, embeddings, image, and speech). Most models share one endpoint per modality; a few use their own model-scoped URL instead — same auth, same request/response shape. You pay only for what you use, in ₹, from a prepaid wallet — no subscription required to start, and ₹50 in free credits on signup.

Base URL

All API requests are made to:

https://api.nabh.cloud/v1

Because the API follows the OpenAI Chat Completions specification, existing OpenAI SDKs and tools work by changing only the base URL and the API key.

curl https://api.nabh.cloud/v1/chat/completions \
  -H "Authorization: Bearer nbh_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3-70b-instruct",
    "messages": [{"role": "user", "content": "Hello from India!"}]
  }'

Every response carries X-Balance-INR (your balance before this request) and X-Request-ID as headers. Non-streaming chat, embeddings, and image responses also include cost_inr and balance_inr in the JSON body — the exact charge and your resulting balance. Streaming responses don't carry a body-level cost (headers are sent before the stream completes), but every streamed chat completion includes a final usage chunk (prompt_tokens / completion_tokens) you can multiply by the model's published rate to compute the exact cost yourself. You are never billed beyond your available balance.

Explore the docs