All Providers Quick Reference

Built into Cherry Studio 60+ providers, this page provides an overview table; after finding the target providerjust fill in the key as instructed to use it. Providers with dedicated documentation have jump links; the rest follow the general steps (Provider Overview) to configure.

Usage Steps

1. Find the target provider(Use Ctrl/⌘+F to search quickly)
2. Click Official website Register an account and obtain an API key
3. In Cherry Studio Settings → Model Services find the corresponding provider, fill in the key, then click "Get model list"
4. Configuration complete

One-line decision

Your needs	Recommended direction
Quick start for beginners, avoid complicated processes	CherryIN or CherryAI
Easiest to access within China	DeepSeek / Moonshot / SiliconFlow / Zhipu
Strongest overseas models	OpenAI / Anthropic / Gemini
One key works across 200 providers	OpenRouter
Fully local, privacy-sensitive	Ollama / LM Studio
Enterprise compliance	Azure OpenAI / AWS Bedrock
Need to Cherry Agent	Anthropic / CherryIN(must support the Anthropic protocol)

Models self-operated by major domestic companies

No need to bypass the Great Firewall, Chinese-language advantages, relatively cheap.

Provider	One-line features	Official website	Dedicated documentation
DeepSeek	The king of cost-effectiveness for coding and reasoning	deepseek.com	→
Moonshot AI (Kimi)	Ultra-long context (up to 2 million Chinese characters)	moonshot.cn	→
ZhiPu (Zhipu)	GLM series, multimodal	bigmodel.cn	—
Doubao (Doubao / Volcano Engine)	Made by ByteDance, affordable	volcengine.com	→
Hunyuan (Tencent Hunyuan)	Tencent ecosystem, suitable for integrating with Tencent's ecosystem	cloud.tencent.com	—
Baidu Cloud (Wenxin Yiyan)	Baidu ERNIE series	cloud.baidu.com	—
Bailian (Alibaba Bailian)	Qwen series, with a vast number of models	bailian.console.aliyun.com	→
BAICHUAN AI	Baichuan large model	baichuan-ai.com	—
MiniMax	Domestic multimodal (voice, video)	minimaxi.com	→
StepFun	StepFun	stepfun.com	—
Yi	01.AI	01.ai	—
LongCat	Meituan LongCat series	longcat.chat	—
Xiaomi MiMo	Xiaomi large model	—	—

Models self-operated by major overseas companies

Top-tier performance; access from China usually requires a proxy.

Provider	One-line features	Official website	Dedicated documentation
OpenAI	GPT series	openai.com	→
Anthropic	Claude series, the preferred choice for Cherry Agent	anthropic.com	→
Gemini (Google)	Google large models	aistudio.google.com	→
Azure OpenAI	Microsoft's hosted OpenAI, enterprise compliant	portal.azure.com	→
VertexAI	Hosted on Google Cloud	cloud.google.com	→
AWS Bedrock	Amazon hosts multiple models	aws.amazon.com/bedrock	—
Mistral	Representative European open-source model	mistral.ai	—
Grok (xAI)	Musk's xAI, with built-in web access	x.ai	→
Perplexity	Search-enhanced chat	perplexity.ai	—

Gateway / aggregation

One key connects to multiple models, with centralized account management.

Provider	One-line features	Official website	Dedicated documentation
CherryAI	Cherry official free trial	—	→
CherryIN	Cherry official paid gateway, dual endpoints (OpenAI + Anthropic)	open.cherryin.cc	→
OpenRouter	Largest overseas aggregation, 200+ models	openrouter.ai	→
AiHubMix	Overseas aggregation	aihubmix.com	—
DMXAPI	Domestic aggregation	dmxapi.cn	—
302.AI	Domestic aggregation	302.ai	—
NewAPI	Self-built gateway (open source)	—	→
OneAPI	Self-built gateway (open source)	—	→
PPIO PAI Cloud	Domestic cloud compute + models	ppio.com	→
BurnCloud	Domestic aggregation	—	—
AIOnly	Domestic aggregation	—	—
ocoolAI	Domestic aggregation	—	—
TokenFlux	Overseas gateway	—	—
Poe	Quora's AI marketplace	poe.com	—
Vercel AI Gateway	Vercel's gateway	vercel.com/ai	—

Ultra-low-latency / high-throughput inference service

Suitable for scenarios that need a sense of "speed" (IM bots, real-time translation, etc.).

Provider	One-line features	Official website	Dedicated documentation
Groq	LPU hardware, millisecond-level response	groq.com	→
Cerebras AI	In-house chips, ultra-large context	cerebras.ai	—
Together	Centralized hosting for open-source models	together.ai	—
Fireworks	Open-source model inference optimization	fireworks.ai	—
Hyperbolic	Inference service, cost-effective	hyperbolic.xyz	—

Domestic cloud + compute services

Provider	One-line features	Official website	Dedicated documentation
Silicon (SiliconFlow)	Largest domestic open-source model hosting	siliconflow.cn	→
ModelScope (ModelScope)	Alibaba's open-source model platform	modelscope.cn	→
Huawei Cloud	Huawei Cloud Pangu	huaweicloud.com	→
Tencent Cloud TI	Tencent Cloud TI platform	cloud.tencent.com	—
Infinigence AI	Domestic compute gateway	infini-ai.com	→
AlayaNew	Domestic inference service	—	—
Qiniu (Qiniu)	Qiniu Cloud AI	qiniu.com	—
Cephalon	Domestic inference	—	—
LANYUN	Domestic inference	—	—
Xirang	Domestic inference	—	—
Infini	Domestic inference	—	—

For embeddings / reranking only

Used only for embeddings or reranking, for use with knowledge bases / global memory.

Provider	One-line features	Official website	Dedicated documentation
Jina	Embeddings, reranking, CLIP, generous free quota	jina.ai	—
VoyageAI	Embedding / reranking specialist	voyageai.com	—

Local inference

Fully offline, protects privacy.

Provider	One-line features	Official website	Dedicated documentation
Ollama	Command-line local inference, the most popular	ollama.com	→
LM Studio	GUI local inference, Apple Silicon friendly	lmstudio.ai	→
GPUStack	Enterprise-grade local inference	gpustack.ai	—
OpenVINO Model Server	Intel-accelerated local inference	openvino.ai	—

Model platforms / others

Provider	One-line features	Official website	Dedicated documentation
Hugging Face	World's largest open-source model community	huggingface.co	—
GitHub Copilot	Microsoft's GitHub coding assistant	github.com/features/copilot	→
GitHub Models	GitHub model marketplace (Beta)	github.com/marketplace/models	—
MiniMax Global	MiniMax overseas version	—	—
SophNet	Domestic model hosting	—	—
PH8	Domestic inference	—	—
Z.ai	Zhipu international version	z.ai	—
nvidia	NVIDIA NIM inference	nvidia.com	—

Custom provider

If the service you use is not in the list above, but provides OpenAI compatibility / Anthropic compatibility / Gemini compatibility any of these protocols, it can be added through Custom provider add it.

Still don't know which one to choose?

Just go with CherryIN or CherryAI — best for beginners to get started quickly. Switch later when you need something more advanced.

---

💡 Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions the official channels provided there.