NovaAPI
Measured metrics
- Overall score
- 6.0 / 10 ★★★
- Stability band
- Very stable
- Uptime
- 100% （Measured here）
- Response latency
- 499 ms
- Model count
- Not detected
- Backend engine
- —
- Verification
- Suspected
- Last checked
- 2026-10-19
- Outbound clicks
- 60 clicks
Uptime basis: Measured here, from 61 valid checks over the last 30 days, per-day reachability (not per request). The resolution is one day — 1% means roughly 0 unreachable days out of 30.
Published rates & minimums
The figures below are published by the service itself on public channels. We only log them, and they are not our measurements — always confirm on the service's own billing page.
The service advertises up to 15% off API calls, plus long-term rewards for referrals
Billing model: Pay-as-you-go
A rate of 1.0 means official list price; 0.3 means you pay 30% of it. Not sure how the maths works out? Run the rate calculator →
About this service
NovaAPI aggregates AI model APIs from outside mainland China. GPT, Claude, Gemini and other families are available. Top-ups can be paid with WeChat Pay / Alipay / USDT / credit cards. It exposes a standard /v1/models endpoint. Check that the host is reachable from your network before committing.
Strengths
- Overseas-hosted, so no China-specific network restrictions
- Exposes a standard /v1/models endpoint (confirmed by our own probe)
- Accepts Alipay, WeChat Pay, credit cards, USDT
Watch out for
- Check reachability from your own network before committing
Our take: A New API based relay whose /v1/models returns 401 (invalid token), confirming a live gateway. The frontend is a lightweight single page with limited public information, so documentation, pricing and the operating entity still need confirmation. Reachability check only.
Model families supported
Current promotions
Ongoing referral rewards when invited friends sign up; credit for new users
Promotions are announced by the service itself and may change or end at any time — check its own page before relying on them.
Daily monitoring log
| Date | Uptime | Avg latency | Samples | Status |
|---|---|---|---|---|
| 2026-10-27 | 100.00% | 499 ms | 1 | 200 |
| 2026-10-26 | 100.00% | 584 ms | 2 | 200 |
| 2026-10-25 | 100.00% | 821 ms | 2 | 200 |
| 2026-10-24 | 100.00% | 545 ms | 2 | 200 |
| 2026-10-23 | 100.00% | 655 ms | 2 | 200 |
| 2026-10-22 | 100.00% | 495 ms | 2 | 200 |
| 2026-10-21 | 100.00% | 468 ms | 2 | 200 |
| 2026-10-20 | 100.00% | 483 ms | 2 | 200 |
| 2026-10-19 | 100.00% | 568 ms | 2 | 200 |
| 2026-10-18 | 100.00% | 519 ms | 2 | 200 |
| 2026-10-17 | 100.00% | 1026 ms | 2 | 200 |
| 2026-10-16 | 100.00% | 514 ms | 2 | 200 |
| 2026-10-15 | 100.00% | 580 ms | 2 | 200 |
| 2026-10-14 | 100.00% | 477 ms | 2 | 200 |
Data sources
howtok.net listing page (published by the service itself)
We are not affiliated with NovaAPI and do not act as its agent, and we do not vouch for its service or the safety of your funds. Figures may lag or contain errors — if you spot one, please report it.
Similar services
Avian
Per the service's own site: Fast AI inference billed per token. DeepSeek V3.2, Kimi K2.5, GLM-5.…
apipro.maynor1024.live
An overseas AI API relay and aggregation service. Model coverage spans Claude, GPT, Gemini. It e…
api.cursorai.art
A globally hosted relay that fronts a range of AI model APIs. Claude, GPT and other families are…
LLM Gateway
The site itself puts it this way: Route, manage, and analyze LLM requests across OpenAI, Anthrop…
MegaLLM
Per the service's own site: The reliable AI gateway for developers. Access GPT-5, Claude Opus 4.…
Requesty
Its own site describes it as: Route every LLM call through one OpenAI-compatible API. Claude, GP…