LogoLMSpeed
O

Nova AI

WebsiteShare on X

once.novai.su

Nova AI is an API platform that aggregates global AI services, offering stable, fast, and low-cost access to large language models for developers.

Models
166 models
From
$0.050/M
Speed
64 tok/s
Updated
6/8/2026
Latency
0.00 s
Created At
2/21/2026
Recharge Rate
¥1.00 per $1 quota

Features

DrawingTaskData Export

API Endpoints

  • Global Acceleration Route
    https://once.novai.su

    For enterprise users and commercial use

  • Asia-Pacific Acceleration Route
    https://2api.novai.su

    CDN optimized

  • Global Acceleration Route
    https://once-cf.novai.su

    Powered by CloudFlare CDN

  • Hong Kong Route
    https://hk.novai.su

    Text-only API. Use other endpoints for images.

  • Direct Load Node
    https://us.novaiapi.com

    From node

Claim this provider

Verify ownership to unlock provider management features:

  • Edit provider name, content, and links
  • Get featured with priority traffic and visibility boost
  • Display a verified badge to build user trust

Leaderboard Rankings

Health
1.0%#302/717

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About Nova AI

Nova AI provides a unified API platform for accessing various large language models, designed to deliver stable, fast, and cost-effective AI services. Key features include:

  • Primary Capabilities: Aggregates multiple AI models through a single API endpoint, simplifying integration for developers.
  • Key Models/Endpoints: Supports models like 2.5pro, with main host URL at https://once.novai.su/v1 and a backup at https://twob.pp.ua/v1.
  • Notable Strengths: Emphasizes stability, speed, and low cost, though specific latency or pricing details are not provided in the content.
  • Typical Use Cases: Suitable for developers building applications that require AI-powered text generation, chatbots, or other language processing tasks.
  • Documentation and Support: Offers documentation at https://docs.novai.su and community support through QQ groups for troubleshooting and updates.
  • Registration and Access: Registration is limited to QQ email addresses, with new users receiving free trial credits for model calls.

Health Check

100%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 209 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

View all 110 models
Model
Input ($/M)
Output ($/M)
Speed
Latency
[次]deepseek-v4.1-flashAuto
$0.020/request---
[ant]claude-opus-4-6Claude
$0.250/request---
[ant]claude-opus-4-6Auto
$0.250/request---
[ant]claude-opus-4-6-thinkingAuto
$0.250/request---
[ant]claude-opus-4-6-thinkingClaude
$0.250/request---
[ant]claude-sonnet-4-6Claude
$0.250/request---
[ant]claude-sonnet-4-6Auto
$0.250/request---
[free]claude-opus-5Auto
FreeFree--
[free]deepseek-v4-pro-0813Auto
FreeFree--
[free]gemini-3.7-flashAuto
FreeFree--
[free]GLM-5.3Auto
FreeFree--
[free]GLM-5.3-flashAuto
FreeFree42.6 t/s28.35 s
[free]gpt-5.6-solAuto
FreeFree--
[free]grok-4-6Auto
FreeFree--
[free]kimi-k3Auto
FreeFree--
[free]qwen3.8-maxAuto
FreeFree--
[次-流抗截]gemini-3.1-pro-preview-thinkingAuto
$0.050/request---
[次]claude-opus-4-5-thinkingClaude
$0.200/request---
[次]claude-opus-4-5-thinkingAuto
$0.200/request---
[次]claude-opus-4-6-thinkingAuto
$0.200/request---
[次]claude-opus-4-6-thinkingClaude
$0.200/request---
[次]claude-opus-4-7-thinkingAuto
$0.200/request---
[次]claude-opus-4-7-thinkingClaude
$0.200/request---
[次]claude-opus-4-8-thinkingClaude
$0.200/request---
[次]claude-opus-4-8-thinkingAuto
$0.200/request---

Showing 25 of 209 model rows

Recent Test Records

TimeModelSpeedLatency
Sep 11, 07:25 PM
[free]GLM-5.3-flash
42.58 tok/s
28.35s
Feb 21, 02:26 PM
[次]gemini-3.1-pro-preview
85.07 tok/s
17.34s

Similar API Provider Alternatives to Compare

Compare Nova AI alternatives against 6 nearby API providers using 450 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
Nova AI

once-novai-su

Nova AI is an API platform that aggregates global AI services, offering stable, fast, and low-cost access to large language models for developers.

Current provider baseline1669$0.125/M64 tok/s9860%
鲨鱼魔法

openai-sharkmagic-top

鲨鱼魔法 (sharkmagic.top) provides access to official paid AI models like Gemini, Claude, and GPT through a unified proxy with OpenAI-compatible API.

  • Faster measured speed
  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
1,57715$7.20/M81 tok/s9980%
OpenRouter

openrouter

A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
6140N/A85 tok/s9990%
NVIDIA NIM

nvidia-nim

NVIDIA NIM provides optimized AI model inference APIs for LLMs, vision, and embedding models through NVIDIA cloud infrastructure.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
1680N/A82 tok/s9970%
Gitee AI

gitee-ai

Gitee AI provides a platform for AI model hosting, inference, and deployment with access to open-source LLMs.

  • Faster measured speed
  • Broader model coverage
2600N/A88 tok/s7280%
WONG公益站

wzw-pp-ua

WONG公益站 is a free, community-driven OpenAI-compatible API relay. It aggregates 70+ AI models from providers like OpenAI, Anthropic, DeepSeek, xAI, Moonshot, and Zhipu AI, offering free API quotas for developers and researchers.

  • Lower average pricing
  • Higher 30-day availability
1550$0.013/M46 tok/s9990%
SkyAI

api-071572-xyz

SkyAI provides an OpenAI-compatible API relay with access to multiple AI models and stable performance.

  • Faster measured speed
  • More free-model options
6414N/A98 tok/s0%

Announcements

ongoing6/14/2026

[Price Reduction Notice] Kiro group price has been reduced to 0.3x. Claude Code group price has been reduced to 1x.

Join the group for more info: QQ group 958019655

ongoing5/30/2026

Free models are now available. If it shows no channel, then it has been taken down; you can switch to other models. [free]gpt-5.5 [free]gpt-image-2

ongoing5/29/2026

@all members

[Announcement]

Due to a system anomaly, data from 03:38 on May 28, 2026 to 14:00 on May 29, 2026 was lost.

Handling plan:

  1. All recharge orders on the site will be fully refunded;
  2. For recharge orders from e-commerce platforms (Taobao, Pinduoduo, etc.), please contact customer service for negotiation;
  3. If you have any questions, please contact customer service.

We apologize for the inconvenience caused. The technical team is actively fixing and optimizing related safeguards. Thank you for your understanding and support.

Platform Operations Team May 29, 2026

Join the group for more info: QQ group 958019655

FAQ

How is privacy protected?

We do not collect any personal data. Only essential server operation data is used, and it never involves anyone's privacy.

Notes

  • Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.
  • Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
  • Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.