Aitoke

www.aitoke.top

Enterprise API distribution and management platform providing unified access to 50+ AI models including OpenAI, Claude, and Gemini with full OpenAI compatibility.

Models: 73 models
From: $0.0082/M
Speed: 37 tok/s
Updated: 7/24/2026

Latency: 0.00 s
Created At: 4/18/2026
Recharge Rate: ¥1.00 per $1 quota

Features

DrawingTaskData ExportCheck-in

Login Methods

GitHubDiscordLinuxDO

API Endpoints

Endpoint 1Historical / Unverified
https://www.uocode.com
Endpoint 2Historical / Unverified
https://us.uocode.com
Endpoint 3Historical / Unverified
https://www.aitoke.top

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%#189/716

Data as of Jul 24, 2026, 12:45 AMRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About Aitoke

Aitoke is an enterprise-grade API distribution and management platform that offers unified access to over 50 mainstream AI models. It provides a single integration point for models from providers like OpenAI, Claude, Gemini, Llama, Mistral, and Midjourney, with full compatibility to the OpenAI API format.

Key features include:

Unified routing and distribution system allowing seamless switching between underlying models and providers
Automatic load balancing for high availability
Management console for user, token, group, and channel administration with quota and concurrency controls
Detailed logging and token-based billing with real-time analytics
Supports 1ms routing speed
Compatible with popular AI applications including NextChat, LobeChat, ChatGPT Next Web, Dify, FastGPT, and Open WebUI
Provides Python integration by simply modifying the base_url in official OpenAI libraries
Reports 99.9% service availability SLA
Offers real-time request status monitoring and cost control tools

Health Check

100%Recent availability

History (72 pts)

PastNow

API Benchmarks & Pricing

Compare 93 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

View all 32 models

Model	Input ($/M)	Output ($/M)
claude-opus-4-6-thinkingClaude_K1通道	$0.171/M	$0.856/M
claude-opus-4-7-thinkingClaude_K1通道	$0.171/M	$0.856/M
gemini-2.5-flash-thinkingGoogle Gemini	$0.0082/M	$0.192/M
gemini-3-pro-highGoogle Gemini	$4.11/M	$24.66/M
gemini-3-pro-lowGoogle Gemini	$0.110/M	$0.658/M
gpt-5.6-lunaGTP Codex 全家桶	$0.027/M	$0.164/M
gpt-5.6-lunaGPT Codex	$0.029/M	$0.173/M
gpt-5.6-lunagptpro	$0.034/M	$0.205/M
gpt-5.6-lunaGPT全家桶-日卡专用	$0.137/M	$0.822/M
gpt-5.6-terraGTP Codex 全家桶	$0.068/M	$0.411/M
gpt-5.6-terraGPT Codex	$0.072/M	$0.432/M
gpt-5.6-terragptpro	$0.086/M	$0.514/M
gpt-5.6-terraGPT全家桶-日卡专用	$0.342/M	$2.05/M
gpt-5.6-solGTP Codex 全家桶	$0.137/M	$0.822/M
gpt-5.6-solGPT Codex	$0.144/M	$0.863/M
gpt-5.6-solgptpro	$0.171/M	$1.03/M
gpt-5.6-solGPT全家桶-日卡专用	$0.685/M	$4.11/M
claude-sonnet-5Claude_AG	$0.058/M	$0.288/M
claude-sonnet-5CC通道2	$0.074/M	$0.370/M
claude-sonnet-5Claude_C3	$0.082/M	$0.411/M
claude-sonnet-5Claude_K1通道	$0.103/M	$0.514/M
claude-sonnet-5CC_Max200号池	$0.370/M	$1.85/M
claude-sonnet-5CC_Max_1	$0.452/M	$2.26/M
claude-sonnet-5CC_Max	$0.493/M	$2.47/M
gpt-image-2-4kIG	$0.0068/request	-

Showing 25 of 93 model rows

Recent Test Records

Time	Model	Speed	Latency
Apr 23, 08:34 AM	claude-opus-4-7	38.49 tok/s	2.68s
Apr 23, 08:29 AM	claude-opus-4-7	33.64 tok/s	1.92s
Apr 23, 08:27 AM	claude-opus-4-7	34.12 tok/s	3.66s
Apr 18, 09:21 AM	claude-sonnet-4-6	43.13 tok/s	2.40s

Similar API Provider Alternatives to Compare

Compare Aitoke alternatives against 6 nearby API providers using 387 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

Provider	Why compare	Models	Free	Avg price	Speed	30d uptime
Aitoke www-aitoke-top Enterprise API distribution and management platform providing unified access to 50+ AI models including OpenAI, Claude, and Gemini with full OpenAI compatibility.	Current provider baseline	73	0	$0.021/M	37 tok/s	9960%
Cuz AI ai-cuz-lab-space Cuz AI runs an OpenAI-compatible relay at ai.cuz-lab.space with broad model coverage, public pricing, and stable throughput for chat and coding workloads.	Lower average pricing Faster measured speed Higher 30-day availability Broader model coverage Same provider category	393	0	$0.020/M	170 tok/s	9980%
CatClaw API www-catclawai-top CatClaw API provides an AI model relay with access to GPT, Claude, and other large language models.	Faster measured speed Higher 30-day availability More free-model options Broader model coverage Same provider category	129	2	N/A	83 tok/s	9980%
初叶🍂Furry API ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users.	Faster measured speed More free-model options Broader model coverage Same provider category	1,021	152	$18.00/M	171 tok/s	2420%
天絮 API tianxu-api Tianxu API provides an AI model relay service with multiple access points and stable connectivity.	Lower average pricing Faster measured speed Broader model coverage Same provider category	759	0	$0.014/M	93 tok/s	9920%
Dext API ai-dext-top Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage.	Lower average pricing More free-model options Broader model coverage Same provider category	667	219	$0.017/M	19 tok/s	3130%
钠 API naapi-cc Na API (naapi.cc) is an OpenAI-compatible LLM API gateway with competitive pricing and stable access to 100+ models from OpenAI, Anthropic, Google, and more.	Lower average pricing Faster measured speed Broader model coverage Same provider category	566	0	$0.0031/M	649 tok/s	9960%

Announcements

default8/30/2026

The multiplier for the GTP Codex family bucket has been reduced because we recently adjusted pricing. Please see the pricing page for the full price. We have also launched two new models: grok-4.5 and grok-4.6.

default8/29/2026

The group monitoring page is currently undergoing maintenance, expected to take 1–2 days. Please be patient during this time; it will not affect normal usage.

default8/27/2026

GPT Codex family bundle is a special offer channel with average stability. The price has been reduced. The GPT Codex regular channel has better stability and the price remains unchanged.

default8/22/2026

Performance degradation: We are currently investigating stability issues with the Claude_K1 and AG channels. Please wait while we work to restore full functionality.

default8/10/2026

The server was inaccessible about 1 hour ago, but it has now been restored and is functioning normally.

default8/8/2026

Currently, because the API address of this site is not working properly, we are now officially switching the API call addresses. There are currently two available addresses:

1: https://ncapi.eu.cc 2: https://apinew.eu.cc

Please replace the API address in time to continue using.

default8/6/2026

Due to poor stability of the model, we have decided to take gpt-5.6-luna offline. Other models are unaffected and can be used normally.

default7/24/2026

The prices of CC Max and CC Max_1 channels have increased by 0.2. Please refer to the pricing plaza for detailed fees.

default7/23/2026

Dear users, due to rising upstream costs and market fluctuations, the price of GPT services will be increased from today. Please check the pricing plaza for detailed fee standards.

default7/21/2026

Due to the current unstable state of GPT services, we will adjust prices at 21:00 on July 21 (GMT+8). After the adjustment, please check the pricing page for the latest prices. No further notice will be given. If the service stabilizes, we will lower prices accordingly.

default7/20/2026

Models under the Google Gemini group have been relisted, using a pay-as-you-go billing model. For specific price details, please visit the pricing plaza.

default7/12/2026

The multiplier prices for the CC Channel 2 and Claude_C3 groups have been reduced. Please check the pricing plaza for specific prices.

default7/11/2026

It is forbidden to use gpt-5.4-mini for immersive translation, distillation tasks, or non-streaming calls.
Once discovered, the account will be directly banned.

This type of usage consumes a large amount of quota and affects normal use by other users, so it is not allowed.

default7/10/2026

Final notice: When using WeChat Pay, please do not select Apple Pay, Google Pay, or bank card (Credit/Debit Card) payment methods. If any of the above methods are used for payment, corresponding fees will be deducted manually.

Please use only WeChat Pay to complete payment. Apple Pay, Google Pay, and bank card (Credit/Debit Card) payments are not supported.

default7/2/2026

We have launched waffo Pancake payment. The minimum payment amount for this payment method is 30 USD. To facilitate normal use for Hong Kong users, we have also launched WeChat Pay payment with no fees. Alipay+ currently requires a certain service provider fee, with a rate of 2.31 HKD + 3%; while waffo Pancake internal payment has no fees.

default7/2/2026

CC_MAX price increased by $0.1. Please check the pricing plaza for detailed prices.

default7/1/2026

CC_MAX price has been reduced by $0.1. Please check the pricing plaza for detailed prices; some groups have launched the Claude Sonnet 5 model.

default6/26/2026

The price of the GTP Codex family bundle has been reduced for the second time today.

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.