Sponsored byFusecodeEnterprise coding API for Claude Code, Codex, and model workflows.
LogoLMSpeed

爱次元API

WebsiteShare on X

aicy.pro

An AI gateway service that provides unified API access to multiple major language models including GPT, Claude, Gemini, and Grok through OpenAI-compatible protocols.

Models
37 models
From
--
Speed
53 tok/s
Updated
8/31/2026
Latency
0.00 s
Created At
3/14/2026
Recharge Rate
¥0.20 per $1 quota

Features

TaskData ExportCheck-in

API Endpoints

  • Global Smart Optimization
    https://aicy.pro

    AI-optimized routing

  • Endpoint 2Historical / Unverified
    https://api.aicy.pro
  • Endpoint 3Historical / Unverified
    https://a.aicy.pro
  • Endpoint 4Historical / Unverified
    https://b.aicy.pro
  • Domestic Premium Route
    https://api.acy7.com

    Recommended for mainland China

  • Domestic Premium Route
    https://api.acy7.cc

    Recommended domestically

  • Global Smart Optimization
    https://gptg.cc

    AI-optimized routing

  • Australia Route
    https://acy7.pro

    Australia route

  • Hong Kong Route
    https://acy7.xyz

    Not as premium as top tier

  • Endpoint 10Historical / Unverified
    https://acy7.com
  • Endpoint 11Historical / Unverified
    https://acy7.cc
  • Kimi Dedicated Route
    https://kimi.6mq.cn

    Kimi model only

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%#238/716

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

About 爱次元API

爱次元API (AiCy API) is an AI gateway service that aggregates multiple large language models under a unified interface. It offers OpenAI-compatible protocols, allowing developers to switch between models like GPT, Claude, Gemini, and Grok by simply changing the base URL and API key.

Key capabilities:

  • Unified model access with consistent API interfaces
  • Stable routing optimized for CLI and streaming outputs
  • Cost control with transparent usage tracking
  • Native tool support for Claude Code, CodeX, and Gemini CLI
  • Third-party client integration guides for desktop and mobile

Typical use cases include development workflows, long conversations, batch tasks, and cost-managed AI deployments. The service emphasizes reduced migration effort and consistent governance from proof-of-concept to production.

Health Check

99%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 12 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
Speed
Latency
grok-imagine-videoGrok-Nx
$0.300/M$0.300/M--
grok-4.3-betaGrok-Nx
$0.150/M$0.150/M--
grok-4.20-0309-non-reasoning-superGrok-Nx
$0.100/M$0.100/M--
grok-4.20-0309-reasoning-superGrok-Nx
$0.100/M$0.100/M--
grok-imagine-imageGrok-Nx
$0.300/M$0.300/M--
grok-4.20-expertGrok-Nx
$0.250/M$0.250/M--
grok-imagine-image-editGrok-Nx
$0.300/M$0.300/M--
grok-imagine-image-liteGrok-Nx
$0.300/M$0.300/M--
grok-4.20-0309-superGrok-Nx
$0.100/M$0.100/M--
grok-imagine-image-proGrok-Nx
$0.300/M$0.300/M--
grok-4.20-fastGrok-Nx
$0.100/M$0.100/M--
gpt-5.4
--53.4 t/s2.92 s

Showing 12 of 12 model rows

Recent Test Records

TimeModelSpeedLatency
Mar 14, 04:22 AM
gpt-5.4
53.41 tok/s
2.92s

Similar API Provider Alternatives to Compare

Compare 爱次元API alternatives against 6 nearby API providers using 188 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
爱次元API

aicy-pro

An AI gateway service that provides unified API access to multiple major language models including GPT, Claude, Gemini, and Grok through OpenAI-compatible protocols.

Current provider baseline3711N/A53 tok/s9940%
TommyLam API

new-api-tommylam-me

TommyLam API offers an OpenAI-compatible API gateway for accessing multiple AI models at competitive rates.

  • Faster measured speed
  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
231100N/A61 tok/s9990%
F2API

api-f2api-com

F2API is an enterprise AI gateway providing a unified OpenAI-compatible interface for accessing multiple large language models.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
1,2620N/A272 tok/s9990%
Koyeb AI Gateway

new-api-koyeb-app

An OpenAI-compatible API gateway deployed on Koyeb, providing access to multiple AI models.

  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
578420N/A33 tok/s9960%
哈基米API站

api-gemai-cc

哈基米API站 offers a unified API gateway for large language models with competitive pricing and stable service.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
3230$0.930/M119 tok/s9990%
DeadlySignal API

deadlysignal

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
2900N/A63 tok/s9970%
PackyAPI

codex-api-packycode-com

PackyAPI (codex-api.packycode.com) is an OpenAI-compatible API relay for Codex and other models via a single interface.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
780$0.041/M69 tok/s9980%

Announcements

success7/29/2026

Customer service WeChat: SJM32500 (for top-ups/recharges)

Customer service WeChat: SJM32500 (for top-ups/recharges)

error7/28/2026

MAX group updated, please reselect and save

Due to difficulty opening Claude, the CCMAX group on this site will increase in price on July 30

success7/10/2026

OpenAI (GPT) released the 5.6 model series, this site has been updated accordingly

success6/16/2026

XAI (Grok) models are now available

composer-2.5 recommended

success6/5/2026

New group added: dedicated image generation group

GPT premium image generation group~ uses the full-powered API

error5/24/2026

The URL may become invalid at any time; add QQ or WeChat to stay connected

success4/16/2026

Customer service WeChat: SJM32500 (for top-ups/recharges)

success4/16/2026

Customer Service QQ: 10938822

default4/16/2026

First-time users, please check the top 'Documentation' first.

Create a token first, then perform a small-scale test.

FAQ

How do I contact customer service?

WeChat: SJM32500 (for top-ups) QQ: 10938822

How to get an API Key?

After logging in, go to 'API Tokens', click 'Add Token' to create. Save the new Key promptly to avoid leakage.

Where can I view consumption and call records?

Go to 'Usage Logs' to view call time, model, token group, and cost.

Why does it say insufficient quota when I have balance?

First, check if both 'Account Quota' and 'Token Quota' are sufficient. Account Quota is the total balance, Token Quota is the individual limit for a specific Key; insufficient in either may trigger the prompt.

Why is the deduction in the logs different from my own estimate?

Different models, groups, and billing methods may vary; the system might also pre-deduct, then adjust based on actual usage by deducting more or refunding the difference, so the final log settlement is authoritative.

Why does it say the model is unavailable or no available channels?

First, confirm that you are calling a model available in 'Personal Settings'; if still erroring, it's usually because the current group hasn't assigned that model, or the channel is temporarily unavailable. Please switch models or try again later.

How do I contact customer service?

WeChat: SJM32500 (for top-ups) QQ: 10938822

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.