All-in-one aggregators 72 services

Relay services that cover several vendor families at once — Claude, GPT, Gemini, Grok and more. Aimed at developers who mix models inside one project and would rather maintain a single integration.

Shell API (api.pumpkinaigc.online)

api.pumpkinaigc.online
Verified Stability: Average /v1/models confirmed China direct

Shell API (api.pumpkinaigc.online) relays AI model APIs from inside mainland China, so requests…

Score 9.3 Uptime 95.08% Latency 1148ms

API易

docs.apiyi.com
Verified Stability: Very stable Claude GPT Gemini China direct

An AI API relay hosted in mainland China and reachable without a VPN. Claude, GPT, Gemini, Grok…

Score 8.5 Uptime 100% Latency 789ms

DeRouter

derouter.ai
Verified Stability: Very stable Claude GPT China direct

DeRouter provides direct-in-China access to AI model APIs, without a VPN or an overseas card. It…

Score 8.5 Uptime 100% Latency 1102ms

LLM Gateway

llmgateway.io
Verified Stability: Very stable Claude GPT Gemini Global / overseas

The site itself puts it this way: Route, manage, and analyze LLM requests across OpenAI, Anthrop…

Score 8.5 Uptime 100% Latency 1694ms Models 299
Verified Stability: Very stable Claude GPT Gemini China direct

A China-based AI API relay offering domestic access to the major model families. Model coverage…

Score 8.5 Uptime 100% Latency 955ms

Requesty

requesty.ai
Verified Stability: Very stable Claude GPT Gemini Global / overseas

Its own site describes it as: Route every LLM call through one OpenAI-compatible API. Claude, GP…

Score 8.5 Uptime 100% Latency 397ms

gpt.ge

gpt.ge
Verified Stability: Very stable Claude GPT Gemini China direct

A China-based AI API relay offering domestic access to the major model families. Claude, GPT, Ge…

Score 8.5 Uptime 100% Latency 662ms

litellm-ai

litellm.ai
Verified Stability: Very stable Claude GPT Gemini Global / overseas

Its own site describes it as: LiteLLM is the open-source AI gateway that puts your full AI stack…

Score 8.5 Uptime 100% Latency 1887ms

MegaLLM

megallm.io
Verified Stability: Stable Claude GPT Gemini Global / overseas

Per the service's own site: The reliable AI gateway for developers. Access GPT-5, Claude Opus 4.…

Score 8.5 Uptime 98.36% Latency 1060ms Models 62

APIYI

apiyi.com
Verified Stability: Very stable Claude GPT Gemini Global / overseas

The site itself puts it this way: A reliable unified AI API gateway for developers and businesse…

Score 8.3 Uptime 100% Latency 1269ms

OpenRouter

openrouter.ai
Verified Stability: Very stable /v1/models confirmed Claude GPT Gemini Global / overseas

The site itself puts it this way: The unified interface for every model. Find the best models &a…

Score 8.3 Uptime 100% Latency 498ms

Poixe AI

poixe.com
Verified Stability: Very stable /v1/models confirmed Claude GPT Gemini China direct

Poixe AI relays AI model APIs from inside mainland China, so requests do not have to leave the r…

Score 8.3 Uptime 100% Latency 804ms Models 178

UIUIAPI

uiuiapi.com
Verified Stability: Stable Claude GPT Gemini China direct

A China-based AI API relay offering domestic access to the major model families. Claude, GPT, Ge…

Score 8.3 Uptime 96.72% Latency 4715ms

aiproxy-io

aiproxy.io
Verified Stability: Unstable Claude GPT Gemini China direct

The site itself puts it this way: The API relay went offline in late 2025. What happened, whethe…

Score 8.3 Uptime 85.25% Latency 1385ms

api-aiproxy-io

api.aiproxy.io
Verified Stability: Poor /v1/models confirmed Claude GPT Gemini China direct

Its own site describes it as: The AIProxy.io API relay went offline in late 2025. What happened,…

Score 8.3 Uptime 83.61% Latency 2514ms
Verified Stability: Poor Claude GPT Gemini Global / overseas

A globally hosted relay that fronts a range of AI model APIs. It covers the Claude, GPT, Gemini,…

Score 8.3 Uptime 77.05% Latency 1429ms
Verified Stability: Poor Claude GPT Gemini Global / overseas

An overseas AI API relay and aggregation service. It covers the Claude, GPT, Gemini, DeepSeek fa…

Score 8.3 Uptime 72.13% Latency 550ms
Verified Stability: Poor Claude GPT Gemini China direct

GitHub (songquanpeng/one-api) relays AI model APIs from inside mainland China, so requests do no…

Score 8.3 Uptime 72.13% Latency 1030ms

犀速AI

xisu.ai
Pending review /v1/models confirmed GPT Claude Gemini Global / overseas

Xisu AI exposes GPT, Claude, Gemini and Grok through both OpenAI-compatible and Anthropic-native…

GPT ×0.1Claude ×0.3Gemini ×0.1
Score 8.0 Latency 4516ms Models 19

AI实验室

aigc369.com
Suspected Stability: Very stable Claude GPT Gemini China direct

An AI API relay hosted in mainland China and reachable without a VPN. Claude, GPT, Gemini and ot…

Score 7.8 Uptime 100% Latency 1046ms

helicone-ai

helicone.ai
Suspected Stability: Very stable Claude GPT Gemini Global / overseas

Per the service's own site: Routing and monitoring for reliable AI apps - the LLMOps platform be…

Score 7.8 Uptime 100% Latency 1189ms

APIMart (apicore.ai)

apicore.ai
Suspected Stability: Very stable Claude GPT Gemini China direct

APIMart (apicore.ai) provides direct-in-China access to AI model APIs, without a VPN or an overs…

Score 7.6 Uptime 100% Latency 9253ms

Jan

cortex.so
Suspected Stability: Very stable Claude GPT Gemini Global / overseas

A globally hosted relay that fronts a range of AI model APIs. Model coverage spans Claude, GPT,…

Score 7.6 Uptime 100% Latency 9981ms

How to choose within this category

There is not enough measured data in this category to justify a recommendation — either few services are listed here, or we have not yet collected enough uptime and latency samples. We do not invent recommendations in that situation: rather than give you a conclusion without evidence, we would rather say plainly that we have none yet.

You can compare the services yourself in the table below, or browse every service in this category sorted by model coverage. Once enough samples accumulate, a recommendation will appear here automatically.

Keep exploring this category

This page shows you what exists; the pages below show you who is more stable, faster and cheaper. Read together, they tell you more than either alone.