Nova API
One OpenAI-compatible API for the providers you configure.
Call chat completions with a Nova API key, stream over SSE, and meter usage against a prepaid API wallet — without rewriting your OpenAI SDK client.
Playground
Try Nova API
Run a real chat completion against your wallet — no SDK required.
Live
Try Nova API
Real requests via a secure session proxy — your Nova key never goes in the URL, and provider secrets never reach the browser.
Sign in to run a real playground request against your API wallet.
Product
What is Nova API?
Nova API exposes a stable, OpenAI-shaped HTTP surface. Your app talks to Nova; Nova routes to allowed, configured providers and settles credits in micro-USD.
Orchestration layer
Auth, routing, fallbacks, usage logs, and billing live in Nova. Provider secrets never leave the server.
Your keys, your wallet
Create nv_live_… keys in My Studio, top up API credits via NowPayments, and track spend in the dashboard.
Compatibility
OpenAI-compatible API
Drop-in baseURL for the official OpenAI SDKs and any client that speaks /v1/chat/completions.
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.NOVA_API_KEY,
baseURL: "https://www.novabrain.online/api/v1"
});
const res = await client.chat.completions.create({
model: "nova-auto",
messages: [{ role: "user", content: "Hello" }],
});Catalog
Available Models
Model IDs and rates come from the live pricing registry. Only enabled rows are shown. nova-auto is a router alias, not a Nova-owned model.
Live from the pricing registry · Nova markup 20% included in Nova prices · updates without redeploy
| Model | Provider | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|
gemini-1.5-flash | gemini | $0.090 | $0.360 | Enabled |
gemini-2.0-flash | gemini | $0.120 | $0.480 | Enabled |
gemini/gemini-2.0-flash | gemini | $0.120 | $0.480 | Enabled |
groq/llama-3.3-70b-versatile | groq | $0.708 | $0.948 | Enabled |
llama-3.1-8b-instant | groq | $0.060 | $0.096 | Enabled |
llama-3.3-70b-versatile | groq | $0.708 | $0.948 | Enabled |
moonshot-v1-8k | kimi | $0.240 | $0.240 | Enabled |
moonshot-v1-auto | kimi | $0.240 | $0.240 | Enabled |
nova-auto | nova | $0.300 | $0.960 | Enabled |
gpt-4o | openai | $3.00 | $12.00 | Enabled |
gpt-4o-mini | openai | $0.180 | $0.720 | Enabled |
openai/gpt-4o | openai | $3.00 | $12.00 | Enabled |
openai/gpt-4o-mini | openai | $0.180 | $0.720 | Enabled |
anthropic/claude-3.5-sonnet | openrouter | $3.60 | $18.00 | Enabled |
google/gemini-2.0-flash-001 | openrouter | $0.120 | $0.480 | Enabled |
openai/gpt-4o-mini | openrouter | $0.180 | $0.720 | Enabled |
openrouter/auto | openrouter | $0.240 | $0.960 | Enabled |
kimi-k3 | starimg | $0.240 | $0.240 | Enabled |
Billing
Transparent Pricing
Input and output prices are read from the pricing registry at request time. Current Nova markup: 20%. Change markup or rates in admin — this page updates without a redeploy.
Charged amount ≈ provider cost × (1 + markup). Wallet balances use integer micro-USD to avoid floating-point drift.
Live from the pricing registry · Nova markup 20% included in Nova prices · updates without redeploy
| Model | Provider | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|
gemini-1.5-flash | gemini | $0.090 | $0.360 | Enabled |
gemini-2.0-flash | gemini | $0.120 | $0.480 | Enabled |
gemini/gemini-2.0-flash | gemini | $0.120 | $0.480 | Enabled |
groq/llama-3.3-70b-versatile | groq | $0.708 | $0.948 | Enabled |
llama-3.1-8b-instant | groq | $0.060 | $0.096 | Enabled |
llama-3.3-70b-versatile | groq | $0.708 | $0.948 | Enabled |
moonshot-v1-8k | kimi | $0.240 | $0.240 | Enabled |
moonshot-v1-auto | kimi | $0.240 | $0.240 | Enabled |
nova-auto | nova | $0.300 | $0.960 | Enabled |
gpt-4o | openai | $3.00 | $12.00 | Enabled |
gpt-4o-mini | openai | $0.180 | $0.720 | Enabled |
openai/gpt-4o | openai | $3.00 | $12.00 | Enabled |
openai/gpt-4o-mini | openai | $0.180 | $0.720 | Enabled |
anthropic/claude-3.5-sonnet | openrouter | $3.60 | $18.00 | Enabled |
google/gemini-2.0-flash-001 | openrouter | $0.120 | $0.480 | Enabled |
openai/gpt-4o-mini | openrouter | $0.180 | $0.720 | Enabled |
openrouter/auto | openrouter | $0.240 | $0.960 | Enabled |
kimi-k3 | starimg | $0.240 | $0.240 | Enabled |
Start free
Free API Credit
New API wallets receive $1 free credit (when enabled in config) so you can verify the gateway before topping up.
Developers
Quick Start
Three steps: account → key → request.
- Create an account, then open the Nova API dashboard.
- Create a key and copy the secret once (nv_live_…).
- Call chat completions:
curl https://www.novabrain.online/api/v1/chat/completions \
-H "Authorization: Bearer nv_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nova-auto",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Capabilities
Features
Chat completions
POST /api/v1/chat/completions with OpenAI-shaped JSON.
Streaming
SSE with data: chunks and a final data: [DONE] — charged once.
Usage & ledger
Per-request usage rows and prepaid wallet debits with idempotent request IDs.
Rate limits
Per-key RPM plus optional monthly token quotas.
Provider routing
nova-auto and explicit model IDs across configured providers.
Credits
NowPayments top-ups into the dedicated API credits wallet.
FAQ
FAQ
Does Nova own GPT, Claude, or Llama?
No. Nova is a gateway/orchestration layer. Upstream providers own their models. We never claim those models as Nova products.
What is nova-auto?
A router alias. The gateway selects an allowed, configured upstream and may fall back between allowed providers.
Where do I manage keys and credits?
In My Studio → Nova API. Create keys, view balance/spend, and add credits via the existing NowPayments flow.
What happens on insufficient credits?
The API returns HTTP 402 with insufficient_credits before calling a provider.
Ship
Create an API Key
Reuse the existing Nova API dashboard — no new control plane.