maolaoapi.com

Maolao API provides an OpenAI-compatible relay for multiple AI models via maolaoapi.com.

Models
46 models
From
$0.017/M
Speed
47 tok/s
Updated
7/17/2026
Latency
0.00 s
Created At
5/9/2026
Recharge Rate
¥1.03 per $1 quota

Features

DrawingTaskData Export

Login Methods

GitHubLinuxDOPasskey妖火网

API Endpoints

  • Endpoint 1Historical / Unverified
    https://canvas.best
  • Backup Node | Direct Connection API Node
    https://api.maolaoapi.com/v1

    Direct connection domain, suitable for overseas servers.

  • Endpoint 3Historical / Unverified
    https://maolaoapi.com
  • Endpoint 4Historical / Unverified
    https://image.maolaoapi.com
  • Endpoint 5Historical / Unverified
    https://api.maolaoapi.com
  • Endpoint 6Historical / Unverified
    https://cnapi.maolaoapi.com
  • Endpoint 7Historical / Unverified
    https://canvas.maolaoapi.com
  • Endpoint 8Historical / Unverified
    https://gpt-image-playground.cooksleep.dev
  • Main API Domain: Auto Routing Domestic & International, Highly Recommended
    https://api.maolaoapi.cc/v1

    Auto routing for domestic and international traffic; highly recommended.

  • Endpoint 10Historical / Unverified
    https://api.maolaoapi.cc
  • Anti-Blocking Endpoint
    http://152.53.239.32:18080/v1

    Use this endpoint if the domain is blocked in regions like Fujian.

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

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

Health Check

100%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 82 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
gpt-5.6-sol-openai-compact
--
gpt-5.6-terra-openai-compact
--
$0.152/M$0.761/M
$0.989/M$4.94/M
$1.14/M$5.71/M
$1.52/M$7.61/M
deepseek-v4-flash-free
--
glm-5.1
--
glm-5.2
--
gpt-5.6-lunaCodex-Plus
$1.71/M$13.69/M
gpt-5.6-lunaCodex-Hack
$2.28/M$18.26/M
gpt-5.6-lunacodex-pro特价
$2.28/M$18.26/M
gpt-5.6-lunaCodex-Pro
$3.42/M$27.39/M
gpt-5.6-terraCodex-Plus
$1.71/M$13.69/M
gpt-5.6-terraCodex-Hack
$2.28/M$18.26/M
gpt-5.6-terracodex-pro特价
$2.28/M$18.26/M
gpt-5.6-terraCodex-Pro
$3.42/M$27.39/M
gpt-5.6-solCodex-Plus
$1.71/M$13.69/M
gpt-5.6-solCodex-Hack
$2.28/M$18.26/M
gpt-5.6-solcodex-pro特价
$2.28/M$18.26/M
gpt-5.6-solCodex-Pro
$3.42/M$27.39/M
$0.061/M$0.304/M
$0.396/M$1.98/M
$0.456/M$2.28/M
$0.609/M$3.04/M

Showing 25 of 82 model rows

Recent Test Records

TimeModelSpeedLatency
May 9, 06:12 AM
gpt-5.5
46.99 tok/s
1.84s

Similar API Provider Alternatives to Compare

Compare Maolao API alternatives against 6 nearby API providers using 242 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
Maolao API

maolaoapi-com

Maolao API provides an OpenAI-compatible relay for multiple AI models via maolaoapi.com.

Current provider baseline460$0.060/M47 tok/s9960%
钱多多 API

api2-aigcbest-top

Provides AI-generated content APIs for various applications, including text and image generation.

  • Lower average pricing
  • Faster measured speed
  • More free-model options
  • Broader model coverage
1,4182$0.0025/M101 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/s10000%
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.

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

deadlysignal

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

Announcements

ongoing8/20/2026

Crazy Thursday · In-platform credit subsidy 💵

The subsidy list is generated based on the snapshot at 2026-08-20 00:00. Eligibility:

  1. Account is active;

  2. Had consumption from Aug 13 to Aug 19, and consumption in the last 7 days ≥ $20;

  3. Historical recharge ≥ $100, or consumption in the last 7 days ≥ $100.

This subsidy covers 225 users, distributing a total of $3800 in in-platform credits, which will be issued gradually based on recent usage.

You can check eligibility via @MaoLao_KFC_Bot. For questions, contact @MaoLaoKFBOT.

————————

🗒Codex-Hack Price Adjustment Notice🔔

Due to market, channel, and risk control cost changes, the Codex-Hack group will be adjusted.

Users who violate terms may receive a refund and have their service terminated on a case-by-case basis.

From 2026-08-20 14:00, the Codex-Hack multiplier will be adjusted to 0.3×.

Please make arrangements in advance. Thank you for your understanding and support!

ENJOY.

warning8/4/2026

⚠️ Please note:

Due to the increasing number of relay channels gradually delisting GPT-5.6-Luna,and the continuous increase in the number of relay parties connecting to our Luna service,overall traffic pressure is rising, and service costs are becoming unsustainable.The Luna model is essentially operating at a loss under the account pool mode. Many relay parties even choose to connect to third-party interfaces instead of using their own account pools. Recently, more and more small relay parties have started connecting to our full-price Luna service, further increasing resource pressure.After comprehensive consideration, we have decided to officially delist GPT-5.6-Luna on August 4 at 3:00 PM.Thank you for your understanding and support. Please make model switching and usage arrangements in advance.
ongoing7/25/2026

CC-MAX-special price closed, migrating to CC-MAX-U at 2 PM.

ongoing7/23/2026

Since low-priced Pro accounts are no longer available, the price will be adjusted at 8:00 AM on July 24 to a multiplier of 0.25.

ongoing7/6/2026

Codex-Team multiplier 0.005 - 0.06

ongoing6/6/2026

CC-MAX-special price new group, multiplier 1

success6/5/2026

Please use infinite canvas for image generation. Generation speed is super fast, 4K is basically within one minute.

default6/2/2026

OpenAI has delisted two models: gpt 5.3codex and gpt5.2. These two models have been removed accordingly.

ongoing5/28/2026

CC-MAX, CC-official transfer have added opus-4-8

error5/26/2026

CC-AWS special price group is unstable, closed.

ongoing5/25/2026

Codex-benefit group 0.05 launched

ongoing5/24/2026

Anthropic launched Deepseek official transfer mapping group for easy jailbreak, pure official KEY, more expensive than official to cover payment fees and package users, for large volume it is recommended to use official.

ongoing5/21/2026

Codex-benefit group will restore 0.05 at 2 PM. Also, let me mention that since last night, the intelligence reduction has been very severe, mainly reflected in the context being heavily cut, feeling only about 128K. The pure Pro channel currently feels normal. Actually, it's because I don't want some new users to see the cheap benefit group and go all out, then come back and say I watered down the model 😭

default5/20/2026

Codex has added a new Codex-Hack group, without filtering, no 500 interception errors. It uses third-party channels, cost is higher than self-built account pools, multiplier is 0.2. Those who want to bypass restrictions can directly switch to this group, so they won't go through self-built account pool interception, switching to third-party channels increases latency.

Codex-benefit group, Codex-PP, Codex-Pro all have sensitive word filtering. If there are sensitive words, they will be intercepted and switched, causing longer delays. It is recommended to use the Hack group directly if that's what you're doing.

ongoing5/16/2026

Claude new official key limited-time promotion group, multiplier 1

FAQ

Why do I keep getting frequent failures or retry prompts?

Common causes include using high-risk prompts like jailbreak or bypass, or temporary upstream service congestion, leading to repeated failures, retries, or messages like "Reconnecting..." or "high demand." Please use the service as intended and avoid sending high-risk prompts.

Can I redistribute the API?

Non-subscription plans can be redistributed; subscription plans cannot.

Can I use it with Immersive Translate?

No, no, no, absolutely not. The translation concurrency is too high and can get your account banned.

Why don't Anthropic models have caching in some clients?

When using the Anthropic endpoint, some clients are not compatible with the OpenAI endpoint for caching.

About reverse engineering, distillation, etc.

<div> <h3>High-Risk Operation Guidelines</h3> <p> For operations requiring jailbreak or reverse engineering, please use groups marked as allowing such operations (e.g., <code>Codex-Hack</code>). Unmarked groups default to prohibiting jailbreak, bypass, reverse engineering, and other high-risk operations. </p> <p> Violations will be handled accordingly: first offense receives a warning; repeated or serious violations result in a permanent ban with no refund. </p> <ul> <li>Do not jailbreak, bypass restrictions, or circumvent limits;</li> <li>Do not engage in prohibited, pornographic, illegal, violent, or black-market content;</li> <li>Do not use malicious commands or attack site security;</li> <li>Do not use for purposes that violate laws or platform rules.</li> </ul> <p> Normal questions and API calls are unaffected. Please use the service responsibly to maintain a good environment. </p> </div>

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.