Documentation

Everything you need to integrate NovaMind AI into your applications. Our API is OpenAI-compatible — swap your base URL and you're done.

Quickstart

Get your first completion in under 2 minutes.

ℹ️ You'll need an API key from your dashboard. Free tier includes 100K tokens per month with no credit card required.

quickstart.py

import requests

response = requests.post(
    "https://novamind.mihirkansagra.com/api/v1/chat",
    headers={"Authorization": "Bearer nm-sk-your-key-here"},
    json={
        "model": "novamind-chat-v2",
        "prompt": "Explain quantum computing in one sentence.",
    }
)
print(response.json()["choices"][0]["message"]["content"])

Authentication

All API requests must include your API key in the Authorization header as a Bearer token.

HTTP header

Authorization: Bearer nm-sk-<your-api-key>

⚠️ Never expose API keys in client-side code. Use environment variables or a secrets manager. Keys can be rotated from your dashboard at any time.

Chat Completions

POST /api/v1/chat — Generate a response from the model given a prompt or message history.

Request parameters

Parameter	Type	Description
model	string required	Model ID (e.g. `novamind-chat-v2`). See Models.
prompt	string	User message for single-turn completions.
messages	array	Array of `{role, content}` for multi-turn conversations.
max_tokens	integer	Maximum tokens to generate. Default: 1024.
temperature	number	Sampling temperature (0–2). Default: 0.7.
stream	boolean	If true, returns a Server-Sent Events stream. Default: false.

Models

Available models via GET /api/v1/models:

novamind-chat-v2 — 200K context, highest quality. Recommended for production.
novamind-chat-v2-fast — 32K context, 3× lower latency. Best for interactive use.
novamind-embed-v1 — Text embedding model, 1536 dimensions.

Rate Limits

Rate limits are enforced per API key:

Tier	RPM	TPM	Concurrent
Free	20	40K	2
Standard	500	1M	20
Enterprise	Unlimited	Unlimited	Custom

Error Codes

Code	Meaning
400	Bad request — missing or invalid parameters
401	Unauthorized — invalid or missing API key
403	Forbidden — insufficient permissions for this resource
429	Rate limit exceeded
500	Internal server error — contact support