AI API Relay Comparison 2026

These reviews are independently written and edited — we currently have no commercial partnership with any provider listed below, and the order reflects our own rating, not a paid placement. Some figures come from providers' own marketing materials; always check the official site for current pricing. Each card shows its own last-verified date.

📌 English rollout in progress: we've translated in-depth reviews for 153 of the 153+ relay providers tracked on the Chinese side of this site, and are adding more over time. Looking for a provider that isn't here yet? Browse the full Chinese-language comparison board →

153 Providers reviewed
87 Mainland direct connect
49 Free / Budget
93 Mid-tier
11 Enterprise

Provider comparison

Sorted by our editorial rating, highest first.

#1 ★ 4.5

Kling AI

Kuaishou's official Kling open platform, an industry-benchmark video generation model, full text-to-video/image-to-video coverage

Mid-tier Mainstream models Direct connect
Read full review →
#2 ★ 4.4

DeepSeek

DeepSeek's official API, with V4-series pricing that upended the market and strong reasoning ability

Free / Budget Mainstream models Direct connect
Read full review →
#3 ★ 4.4

Zhipu AI GLM

Official Zhipu API — GLM-4.7-Flash permanently free, 200K context + 59.2% SWE-bench, mainland direct connect

Free / Budget Mainstream models Direct connect
Read full review →
#4 ★ 4.4

Krea AI

Proprietary Krea 2 models plus aggregated Nano Banana/Seedance/Kling/Veo access, $83M raised, led by a16z and Bain

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#5 ★ 4.3

Groq Cloud

Powered by purpose-built LPU chips, among the fastest inference speeds in the world, a generous free tier for open-source models

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#6 ★ 4.3

Helicone

0% markup pass-through, built-in LLM observability, open-source and self-hostable, full logging/cost/session tracking

Mid-tier Mainstream models Proxy required
Read full review →
#7 ★ 4.3

nexos.ai

Founded by the Nord Security team, €30M Series A, an enterprise security/compliance AI gateway

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#8 ★ 4.3

PixVerse

AIsphere's short-video generation model, a unicorn valued at over $2B, backed by Alibaba and CDH

Enterprise Mainstream models Direct connect
Read full review →
#9 ★ 4.3

Runware

Lowest-priced image/video generation API on the market, $50M Series A, millisecond-scale inference infrastructure

Free / Budget Full coverage (600+) Proxy required
Read full review →
#10 ★ 4.2

Alibaba Cloud Bailian

Alibaba Cloud's official AI platform, enterprise-grade SLA, Alibaba's proprietary Qwen model series

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#11 ★ 4.2

Cloudflare AI Gateway

Free AI traffic control layer — caching, rate limiting, monitoring, edge acceleration

Free / Budget Full coverage (600+) Proxy required
Read full review →
#12 ★ 4.2

Fal AI

Ultra-fast Flux-series image generation, LoRA fine-tuning, the top choice for creative AI workflows

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#13 ★ 4.2

LingyaAI

Mainland dedicated line, 600+ models unified, corporate VAT invoicing available — built for long-running production and enterprise compliance

Mid-tier Full coverage (600+) Direct connect
Read full review →
#14 ★ 4.2

Moonshot AI (Kimi)

Kimi's official API — 256K ultra-long context, standout document processing and coding ability

Mid-tier Mainstream models Direct connect
Read full review →
#15 ★ 4.2

NoneLinear

480+ models, 99.99% SLA, the top choice for production-grade enterprise use

Enterprise Broad coverage (100+) Direct connect
Read full review →
#16 ★ 4.2

OpenRouter

A cross-vendor multi-model aggregator — 400+ models across 70+ providers, one API key to call OpenAI/Anthropic/Google/Meta/Mistral and more

Mid-tier Full coverage (600+) Proxy required
Read full review →
#17 ★ 4.2

Portkey

Now part of Palo Alto Networks — the core AI gateway for Prisma AIRS; unified access to 1600+ models, full LLMOps suite

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#18 ★ 4.2

SiliconFlow

Domestic open-source model cloud hosting — DeepSeek, Qwen, GLM and 100+ models, an in-house inference engine plus domestic chip support

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#19 ★ 4.2

Together AI

Large-scale open-source model compute aggregation — 100+ models behind one API, suited to both research and enterprise use

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#20 ★ 4.2

TokenRiver

Enterprise-grade AI large-model intelligent gateway, 650+ models, ¥1=$1 exchange-rate advantage, multi-channel automatic failover, redirect destination for the former ShiyunApi

Mid-tier Full coverage (600+) Direct connect
Read full review →
#21 ★ 4.2

Vercel AI Gateway

0% markup, $5 free credit, zero data retention (ZDR), the top choice for frontend developers

Mid-tier Mainstream models Proxy required
Read full review →
#22 ★ 4.1

Fireworks AI

Enterprise-grade inference for open-source models, deep Function Calling optimization, ultra-low-latency SLA

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#23 ★ 4.1

Jina AI API

One key, one token pool for Embeddings + Reranker + Reader — 10M free tokens, no credit card required

Free / Budget Mainstream models Proxy required
Read full review →
#24 ★ 4.1

Lambda Labs

GPU cloud compute + open-model inference; rebranded as Lambda, 60-70% cheaper than mainstream clouds, a top pick for AI research

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#25 ★ 4.1

Laozhang API

A well-known, long-established Chinese Claude relay, priced at parity with official rates, with a strong reputation for stability — a solid first choice if you don't want to deal with headaches

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#26 ★ 4.1

n1n.ai

Enterprise unified LLM API gateway — one key for 400+ models, ¥20 free credit for new users

Free / Budget Mainstream models Direct connect
Read full review →
#27 ★ 4.1

Requesty

EU-friendly, 600+ models, GDPR-compliant, 20ms failover

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#28 ★ 4.1

Weelinking

99.99% SLA, 200+ models, multi-layer redundancy — a stable first choice for enterprise production environments

Enterprise Broad coverage (100+) Proxy required
Read full review →
#29 ★ 4.0

4SAPI / Starlink 4SAPI

Enterprise-grade "self-healing routing system" + enterprise account pool, focused on low latency and high concurrency — frequently tops reviews for AI coding assistants and multimodal use cases

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#30 ★ 4.0

AnPin AI

1Gbps dedicated line + multi-node routing, 99.99% stability promise, admin responds in real time on X

Free / Budget Mainstream models Direct connect
Read full review →
#31 ★ 4.0

API Yi

Long-established AI API aggregator, 300K monthly visits, broad frontier-model coverage

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#32 ★ 4.0

Zhipu AI (BigModel)

Zhipu's official GLM flagship: GLM-5.2 (1M context) in production, GLM-5.3 coming soon, multimodal AI, top-tier Chinese-language capability

Mid-tier Mainstream models Direct connect
Read full review →
#33 ★ 4.0

Cohere API

Embeddings, reranking, and text generation in one — a top pick for RAG engineers

Mid-tier Mainstream models Proxy required
Read full review →
#34 ★ 4.0

DeepInfra

Low-latency inference for open-source models, extremely transparent low pricing, supports crypto payment, includes image-generation models

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#35 ★ 4.0

EasyRouter

From Fu Sheng, 15% off storewide, 40+ model providers, DeepSeek discounts up to 75% off

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#36 ★ 4.0

HuggingFace Inference API

One-click access to hundreds of thousands of open-source models, the go-to for the ML community

Free / Budget Full coverage (600+) Proxy required
Read full review →
#37 ★ 4.0

hvoy.ai

A relay-station directory and review aggregator — not a relay itself, it helps you find the right one

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#38 ★ 4.0

Lepton AI

Former ex-Meta open-model inference platform, now part of NVIDIA DGX Cloud (lepton.ai redirects to NVIDIA)

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#39 ★ 4.0

01.AI (Lingyi Wanwu)

Founded by Kai-Fu Lee, dual open/closed-source Yi series, standout multilingual capability

Mid-tier Mainstream models Direct connect
Read full review →
#40 ★ 4.0

Martian

Former commercial LLM-routing pioneer; the site is now Thesean AI, a research lab for best-execution LLMs

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#41 ★ 4.0

Mistral AI API

Europe's leading open-source AI player, GDPR-compliant, low-priced Codestral code generation

Mid-tier Mainstream models Proxy required
Read full review →
#42 ★ 4.0

Modal

On-demand serverless GPU, minimal-friction deployment for custom model inference

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#43 ★ 4.0

ModelScope

Alibaba's open-source model community, with a free inference tier for Qwen/DeepSeek

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#44 ★ 4.0

Not Diamond

The most powerful intelligent model router for coding agents — 20%+ cost savings at frontier quality

Mid-tier Mainstream models Proxy required
Read full review →
#45 ★ 4.0

Novita AI

200+ open-source models, dedicated image generation, low-cost global inference

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#46 ★ 4.0

PackyAPI

An early domestic relay optimized specifically for Claude Code, an active community, a $1 new-user bonus, a top pick for coding workflows

Mid-tier Mainstream models Direct connect
Read full review →
#47 ★ 4.0

Perplexity API

Search-augmented AI, real-time web retrieval, built-in citations

Mid-tier Mainstream models Proxy required
Read full review →
#48 ★ 4.0

PoloAPI

Balances stability with multi-model coverage, built around "set it up once and let it run," with enterprise governance features like usage stats and auditing

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#49 ★ 4.0

Replicate

Open-source model aggregation + custom model deployment, a leading platform for image/video generation, supports publishing private models

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#50 ★ 4.0

RunPod

Per-second billed GPU cloud, community compute pool, 70% cheaper than AWS

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#51 ★ 4.0

Segmind

Flux/SD image generation from as low as $0.001/image, a top pick for high-volume creative generation

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#52 ★ 4.0

Unify AI

No-setup AI agent teammates, accessing all models from 8 providers incl. OpenAI/Google/DeepSeek/Anthropic

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#53 ★ 4.0

Unity2.ai

30 billion+ tokens processed daily, a top pick for high-concurrency enterprise relay

Enterprise Mainstream models Direct connect
Read full review →
#54 ★ 4.0

Vidu

Shengshu Technology's Vidu video-generation model, one of the first domestic Sora-class video models with an official open API

Free / Budget Mainstream models Direct connect
Read full review →
#55 ★ 4.0

WaveSpeedAI

1000+ image/video generation models accelerated in one platform, sub-second output, Flux/Seedance/Kling all in one place

Mid-tier Full coverage (600+) Proxy required
Read full review →
#56 ★ 3.9

Anyscale

From the team behind the Ray framework, enterprise-grade high-concurrency deployment and fine-tuning for open-source models

Enterprise Broad coverage (100+) Proxy required
Read full review →
#57 ★ 3.9

Eden AI

Single API aggregating OpenAI/Anthropic/Google, with built-in fallback routing

Mid-tier Full coverage (600+) Proxy required
Read full review →
#58 ★ 3.9

FlintAPI

Smart-routing SaaS — subscription + usage overage, 30+ Chinese LLMs under one API, $5 free credit for new users

Mid-tier Mainstream models Direct connect
Read full review →
#59 ★ 3.9

FlowBar

Dual coverage of domestic + global models, 80+ model routes, 50,000 trial tokens for new users, USD pay-as-you-go, production-grade reliability

Mid-tier Mainstream models Proxy required
Read full review →
#60 ★ 3.9

Inworld Router

220+ models with 0% markup, intelligent conditional routing, optimized for coding agents and AI companions

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#61 ★ 3.9

Privnode

$10 signup credit, deep Claude Code integration, focused on coding models

Mid-tier Mainstream models Direct connect
Read full review →
#62 ★ 3.9

ProAI API

Rated by multiple communities as the most balanced, trustworthy choice — solves connectivity problems while keeping costs in check, with three-way Claude/GPT/Gemini coverage

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#63 ★ 3.9

RightCode

Coding-focused, top up from ¥1, clear documentation, Sonnet as low as ¥0.9/M

Free / Budget Mainstream models Direct connect
Read full review →
#64 ★ 3.9

RunAPI

A mainland OpenRouter alternative — 300+ models with smart routing, Claude Code/OpenClaw support, runapi.host for mainland direct connect

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#65 ★ 3.8

AIFast.club

444+ models with mainland direct connect, recharge volume discounts (up to 7.5% off), a real-time status monitoring dashboard, unified single-key management

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#66 ★ 3.8

AiHubMix

Developer-friendly integration, permanent free testing tier, Prompt Caching support, solid documentation

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#67 ★ 3.8

Atlas Cloud

Image/video generation aggregator (Seedance/MiniMax/GPT Image etc.), 300+ models, transparent per-second billing

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#68 ★ 3.8

AzAPI

Multimodal creative-model aggregator: MJ/Suno/Luma/Kling/Flux/Udio; ICP-filed .com.cn domain; multi-group FX (Azure ¥0.4/USD)

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#69 ★ 3.8

Baidu Qianfan

Official Baidu platform, ERNIE model family, enterprise-grade SLA, supports model fine-tuning

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#70 ★ 3.8

ByteCat

Built for code engineers — full Codex Linux/Windows setup guides, mainland direct connect, AI coding model specialist

Mid-tier Mainstream models Direct connect
Read full review →
#71 ★ 3.8

CloseAI

Self-described largest enterprise-grade AI relay platform in Asia, native support for the OpenAI/Claude/Gemini protocols, DPA data agreements available

Enterprise Broad coverage (100+) Direct connect
Read full review →
#72 ★ 3.8

JiekouAI

Full model coverage, subscription plans + pay-as-you-go, dedicated Cloud Code product, 30-second integration

Mid-tier Mainstream models Direct connect
Read full review →
#73 ★ 3.8

LinkAi

Clear documentation, high bonus ratio on large top-ups — ¥100 gets you ¥30 free — covers both Claude and GPT

Mid-tier Mainstream models Direct connect
Read full review →
#74 ★ 3.8

MegaLLM

70+ models aggregated through official channels, stable and highly available, a global AI API relay for mid-to-high-end needs

Mid-tier Mainstream models Proxy required
Read full review →
#75 ★ 3.8

MoleAPI

Single API unifying GPT-4o/Claude/Gemini, <50ms direct-connect latency, OpenAI-format compatible, free credit for new signups

Mid-tier Mainstream models Direct connect
Read full review →
#76 ★ 3.8

OAIPro

Official-channel relay, priced at parity with official rates, high stability

Mid-tier Mainstream models Direct connect
Read full review →
#77 ★ 3.8

ofox.ai

Unified LLM gateway covering 100+ models including GPT/Claude/DeepSeek, built around Claude compatibility and undegraded official direct-source access

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#78 ★ 3.8

OpenClaw

An open-source personal AI assistant — free, self-hosted, can reuse subscription/gateway/local models

Free / Budget Mainstream models Direct connect
Read full review →
#79 ★ 3.8

Huawei Cloud Pangu

Huawei's in-house large model, a top choice for high-compliance finance/government/healthcare scenarios

Enterprise Mainstream models Direct connect
Read full review →
#80 ★ 3.8

Relaydance

Pivoted to video-generation relay: one API for Seedance 2.0/2.5, plus Claude/Grok text and image models

Mid-tier Mainstream models Direct connect
Read full review →
#81 ★ 3.8

UnoRouter

Multi-model aggregation, 300+ models (44+ upstreams), 253 free models, subscriptions with 2x credit

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#82 ★ 3.8

WinToken

Generous new-site bonus, roughly ¥113 in new-user trial credit, dual subscription/pay-as-you-go modes, broad model coverage

Mid-tier Mainstream models Direct connect
Read full review →
#83 ★ 3.8

XycAi (Xingdao Intelligence)

Compliance-certified + Kling AI, a domestic/international mixed-model enterprise relay

Mid-tier Mainstream models Direct connect
Read full review →
#84 ★ 3.8

YKH.AI

Minimalist pricing, Lite multiplier 0.2, performance-first positioning

Free / Budget Mainstream models Direct connect
Read full review →
#85 ★ 3.8

Getimg.ai

All-in-one image generation + editing SaaS, bootstrapped and profitable for years, 3.5M+ monthly visits, creator-friendly

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#86 ★ 3.8

MiniMax Open Platform

MiniMax's official open platform — text, image, video, speech and music all behind one API

Mid-tier Mainstream models Direct connect
Read full review →
#87 ★ 3.7

AI21 Labs API

Jamba hybrid architecture, low-cost long context, enterprise NLP specialization

Mid-tier Mainstream models Proxy required
Read full review →
#88 ★ 3.7

AICloud Feiyun

50 free Sonnet calls given away daily, low-price direct connect to Claude

Mid-tier Mainstream models Direct connect
Read full review →
#89 ★ 3.7

35.AIGCBEST

OpenAI-focused relay (now rebranded 'Qianduoduo API'), Azure pricing structure, exchange rate around 1.5¥/USD, stable and reliable

Mid-tier Mainstream models Direct connect
Read full review →
#90 ★ 3.7

AIMLAPI

1000+ models via one endpoint — the go-to multi-model aggregator for overseas developers

Mid-tier Full coverage (600+) Proxy required
Read full review →
#91 ★ 3.7

ChatFire

Low-price multimodal aggregation, ¥0.5-1/USD exchange rate, a mix of domestic and international models, includes image and video generation

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#92 ★ 3.7

Claude API

Focused Claude relay, launched April 2026, supports image generation, ¥1 trial credit, competitively priced Opus access

Mid-tier Mainstream models Direct connect
Read full review →
#93 ★ 3.7

DigitalOcean Gradient

An AI inference platform for the DigitalOcean developer ecosystem, pay-as-you-go open-source models

Free / Budget Mainstream models Proxy required
Read full review →
#94 ★ 3.7

DMXAPI

480+ model multimodal aggregator, one-stop coverage of text/image/video, enterprise-grade stability

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#95 ★ 3.7

DuckCoding

$1 signup credit, tiered pricing, corporate invoicing supported, focused on coding use cases

Mid-tier Mainstream models Direct connect
Read full review →
#96 ★ 3.7

Tencent Cloud Hunyuan

Tencent's official Hunyuan model, deeply integrated with the Tencent Cloud ecosystem

Mid-tier Mainstream models Direct connect
Read full review →
#97 ★ 3.7

IKunCode

A coding-focused relay with an active QQ community, pure pay-as-you-go with no plans, covers Claude Fable 5/GPT-5.6 and other newest flagships

Mid-tier Mainstream models Direct connect
Read full review →
#98 ★ 3.7

NodAPI

Fast multi-model aggregation, 545+ models, low-latency mainland direct connect, Alipay/WeChat/Stripe

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#99 ★ 3.7

Poixe AI

Operating since 2024, 17+ providers / 8 model families covered, free models + level-based discounts

Mid-tier Mainstream models Direct connect
Read full review →
#100 ★ 3.7

UU API

MAX account pool, image generation at ¥0.04/image, ¥1 new-user bonus

Free / Budget Mainstream models Direct connect
Read full review →
#101 ★ 3.7

iFlytek Spark

iFlytek's official platform — strong on both speech and text, the new Astron MaaS platform, vertical strength in education and healthcare

Mid-tier Mainstream models Direct connect
Read full review →
#102 ★ 3.7

ModelsLab

One API replacing 10+ image/video/speech vendors, 10,000+ community models, claimed 99.9% uptime

Free / Budget Full coverage (600+) Proxy required
Read full review →
#103 ★ 3.6

302.AI

Pay-as-you-go with zero monthly fee — an enterprise-grade AI resource platform offering "one-stop access to every mainstream model," with balances that never expire

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#104 ★ 3.6

B.AI

Full model lineup + USDT/crypto payment, privacy-friendly, no real-identity binding required

Mid-tier Mainstream models Direct connect
Read full review →
#105 ★ 3.6

Bob API

Solo-developer style, high-quality mainland direct connect, mainstream models, good for personal projects

Mid-tier Mainstream models Direct connect
Read full review →
#106 ★ 3.6

Glama AI Gateway

An AI gateway with transparent price comparison, quick multi-vendor switching for experiments

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#107 ★ 3.6

Quanzil API

Full-coverage aggregated relay, 454+ models, WeChat/Alipay/crypto payments, invoicing available

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#108 ★ 3.6

KoalaAPI

Specializes in integrating mainstream overseas models (Gemini/ChatGPT/Claude), claims 99.7%+ success rate for Claude 4.5

Free / Budget Mainstream models Direct connect
Read full review →
#109 ★ 3.6

MNAPI

Cross-vendor quality monitoring, all-in-one aggregation, 239+ models (Claude/GPT/Gemini/Grok/image & video)

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#110 ★ 3.6

Poe API

From Quora, subscription-based multi-model API, quick access to mainstream AI capabilities

Mid-tier Mainstream models Proxy required
Read full review →
#111 ★ 3.6

Sub2API

A subscription-pooling relay station, group-buy-style low-cost shared access to Claude Max capacity

Free / Budget Mainstream models Direct connect
Read full review →
#112 ★ 3.6

UiUiAPI

300+ large-model aggregation, enterprise-grade high-concurrency design, claims official-channel sourcing with transparent, quantified discount rates

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#113 ★ 3.6

XJAI (Hunter API)

Now rebranded 'Hunter API', multi-model aggregation, exchange rate around 1¥/USD, 533+ model coverage

Free / Budget Mainstream models Direct connect
Read full review →
#114 ★ 3.6

Yinhe API

$0.4 signup bonus, dedicated Claude Code optimization, a good pick for lightweight testing

Free / Budget Mainstream models Direct connect
Read full review →
#115 ★ 3.6

RunComfy

Cloud-hosted ComfyUI with one-click deploy, serverless workflow API, no GPU environment to set up

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#116 ★ 3.5

147API / 147AI

The "go-to pick" in multiple reviews — highly compatible interface, RMB settlement, enterprise-grade aggregation relay

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#117 ★ 3.5

AiGoCode

Subscription + pay-as-you-go; ¥50=$50 credit exchange (1:1); mainstream model coverage; try before you subscribe

Mid-tier Mainstream models Direct connect
Read full review →
#118 ★ 3.5

Boluotu AI

⚠️ Announced pivot to enterprise-only: personal top-ups and new registrations closed; 1044+ models incl. newest flagships

Enterprise Full coverage (600+) Direct connect
Read full review →
#119 ★ 3.5

Chutes

Low-latency hosting of SOTA open-source models (Kimi/GLM/DeepSeek/Qwen etc.); pay-as-you-go + subscriptions; unified OpenAI-compatible API

Free / Budget Mainstream models Proxy required
Read full review →
#120 ★ 3.5

GGWK1

OpenAI/Claude/Gemini three-family aggregation, ¥0.6-1/USD exchange rate, mainland direct connect

Free / Budget Full coverage (600+) Direct connect
Read full review →
#121 ★ 3.5

Lumin AI

Launched in 2026; original luminai.cn has moved to luminai.cc, and the main domain now requires a proxy

Mid-tier Mainstream models Proxy required
Read full review →
#122 ★ 3.5

MKEAI

Low-latency mainland direct connect to Claude/GPT/Gemini/Grok/DeepSeek, fast roll-out of new models (Grok 4.6/Gemini 3.7/Opus 5), new-user registration currently closed

Free / Budget Mainstream models Direct connect
Read full review →
#123 ★ 3.5

No.1-API

A one-stop model-aggregation relay with well-documented interfaces, a unified entry point for Claude/GPT/Gemini/DeepSeek

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#124 ★ 3.5

StepFun

StepFun's official platform, Step-3.x series, multimodal flagship plus voice and image, low latency

Mid-tier Mainstream models Direct connect
Read full review →
#125 ★ 3.5

TokenMix

Multi-model aggregation, flexible payment options, serves developers at home and abroad

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#126 ★ 3.5

V-API

Multi-model direct-connect relay covering Claude/GPT/Gemini/DeepSeek/Grok, stable mainland-China direct connect

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#127 ★ 3.5

YunWu API

500+ aggregated models, ¥0.5/USD exchange rate, free daily GPT-4o calls via GitHub login

Free / Budget Broad coverage (100+) Direct connect
Read full review →
#128 ★ 3.5

Zhihui API

A new 2026 platform covering the GPT-5.6 / Claude Opus / Gemini / Grok families, with tiered recharge bonuses for members

Mid-tier Mainstream models Direct connect
Read full review →
#129 ★ 3.4

Boxying

Ultra-low prices: Claude at 0.3x official, Codex at 0.21x, ¥1 = $1 FX; lightweight domestic relay

Free / Budget Mainstream models Direct connect
Read full review →
#130 ★ 3.4

DawCode

A new 2026 platform, daily check-in rewards, ¥4 new-user trial credit

Mid-tier Mainstream models Direct connect
Read full review →
#131 ★ 3.4

Nio API

Brand upgraded to newapi.gs, wildcard subdomains to resist blocking, currently GPT/Gemini-focused, legacy API stays compatible

Mid-tier Mainstream models Direct connect
Read full review →
#132 ★ 3.3

Yiye Zhiqiu API

No minimum top-up, lightweight and test-friendly, zero-barrier proof of concept

Free / Budget Mainstream models Direct connect
Read full review →
#133 ★ 3.2

UniAPI

OpenAI/Claude/Gemini three-way coverage + Midjourney/Suno/Kling and other multimodal models, mainland direct connect, channel-discount billing

Mid-tier Broad coverage (100+) Direct connect
Read full review →
#134 ★ 3.0

Shenma Relay API

2557 multimodal models covered (text/image/audio/video), claims to be the most in the industry, pay-as-you-go with mainland direct connect

Free / Budget Full coverage (600+) Direct connect
Read full review →
#135 ★ 2.8

GPTGOD

A reverse-engineered ultra-low-price relay, exchange rate around ¥0.6/USD — extremely cheap but stability is not guaranteed

Free / Budget Mainstream models Direct connect
Read full review →
#136 ★ 2.0

AIAPIpk

Discontinued (verified 2026-08-16): the domain no longer resolves; the comparison platform is unreachable

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#137 ★ 2.0

Baichuan API

Discontinued (verified 2026-08-16): the domain no longer resolves; service unreachable

Mid-tier Mainstream models Proxy required
Read full review →
#138 ★ 2.0

Banana AI

Sunset: the serverless GPU inference platform was shut down on 2024-03-31

Mid-tier Broad coverage (100+) Proxy required
Read full review →
#139 ★ 2.0

Chien API

Discontinued (verified 2026-08-16): the domain no longer resolves; service unreachable

Mid-tier Mainstream models Proxy required
Read full review →
#140 ★ 2.0

Cooper-API

Discontinued (verified 2026-08-16): the domain no longer resolves; service unreachable

Mid-tier Mainstream models Proxy required
Read full review →
#141 ★ 2.0

GPTAPI.US

Discontinued (verified 2026-08-16): the domain is parked; service unavailable

Mid-tier Mainstream models Proxy required
Read full review →
#142 ★ 2.0

lxg2it ModelRouter

Discontinued (verified 2026-08-16): the domain no longer resolves; service unreachable

Free / Budget Broad coverage (100+) Proxy required
Read full review →
#143 ★ 2.0

Meshs One

Discontinued (verified 2026-08-16): site unreachable; service unavailable

Mid-tier Mainstream models Proxy required
Read full review →
#144 ★ 2.0

NanoBanana

Pivoted away from relay service (verified 2026-08-16): now a free Nano Banana image tool site

Mid-tier Mainstream models Proxy required
Read full review →
#145 ★ 2.0

NativeAI API

Pivoted away from relay service (verified 2026-08-16): now the site of a Japanese software-development company

Enterprise Mainstream models Proxy required
Read full review →
#146 ★ 2.0

OAIPlus

Discontinued (verified 2026-08-16): site unreachable; service unavailable

Mid-tier Mainstream models Proxy required
Read full review →
#147 ★ 2.0

PaintBot

Discontinued (verified 2026-08-16): site unreachable; service unavailable

Free / Budget Mainstream models Proxy required
Read full review →
#148 ★ 2.0

SBGPT

Discontinued (verified 2026-08-16): the domain is for sale; service has shut down

Free / Budget Mainstream models Proxy required
Read full review →
#149 ★ 2.0

Sulian AI

Discontinued (verified 2026-08-16): origin server unresponsive; service unavailable

Mid-tier Mainstream models Proxy required
Read full review →
#150 ★ 2.0

TomCat API

Discontinued (verified 2026-08-16): the domain no longer resolves; service unreachable

Mid-tier Mainstream models Proxy required
Read full review →
#151 ★ 2.0

Xingtu API

Redirected to an unrelated site; no longer a relay service (verified 2026-08-16)

Enterprise Broad coverage (100+) Proxy required
Read full review →
#152 ★ 2.0

ZHTec API

Discontinued (verified 2026-08-16): site unreachable; service unavailable

Free / Budget Mainstream models Proxy required
Read full review →
#153 ★ 0.0

ShiyunApi ⚠️ Discontinued → TokenRiver

Discontinued; successor brand is TokenRiver 词元之河 (tokenriver.cn), now focused on domestic Chinese models

Enterprise Mainstream models Direct connect
Read full review →

FAQ

What is an AI API relay, and why do mainland China developers use one?

An AI API relay (also called an API reseller) buys official API capacity from OpenAI, Anthropic, Google and others in bulk, then resells access at a lower barrier to entry through an OpenAI-compatible endpoint. For mainland China users, relays solve three problems at once: signing up without a card tied to an unsupported region, paying in RMB via Alipay/WeChat Pay, and reaching the model through a mainland direct-connect node instead of a VPN.

How is a relay different from the official API?

Technically, a relay exposes the same OpenAI-compatible interface as the official API — you only need to point base_url at the relay and keep the rest of your code unchanged. The differences are in price (often 10-40% below official pricing, though not always), reliability (depends entirely on the relay's own operations), and model fidelity (some relays quietly substitute a cheaper model for the one you requested). Picking a trustworthy relay is the whole game.

How do I tell if a relay is trustworthy?

Five things worth checking: (1) a real operating entity behind the site, not an anonymous side project; (2) the exact model versions are stated clearly, not vague marketing language; (3) independent, third-party usage reports exist somewhere online; (4) pricing is plausible — anything far below what the official API costs to run is a red flag for quietly-downgraded models; (5) small top-ups are supported, so you can test with a small amount before committing a large balance.

Why isn't every provider reviewed here in English?

We track 153+ relay providers on the Chinese side of the site, and English coverage is now essentially complete — every review here has been independently written and verified, the same as its Chinese counterpart. A small handful of the newest additions haven't been translated yet; if the provider you're looking for isn't listed here, the full Chinese-language comparison board always covers all of them.