2025 AI Provider Support | 2025 年 AI 服务商支持

[arvinxx]

Since the launch of LobeChat's Provider, it has integrated with over 40 model service providers, witnessing the vigorous development of the AI field alongside the industry. Considering that this year is also a brand new beginning, I am posting again to record this year's model service provider support needs. Everyone is welcome to leave a message~

LobeChat 自开放 Provider 以来，已经集成了 40+ 模型服务商，和行业一起见证了 AI 领域的蓬勃发展。考虑到今年也是全新的一个开始，因此重新另外一贴记录今年的模型服务商支持需求。欢迎大家留言~

• 2024 详见： 2024 Model Providers support | 2024 年模型服务商支持 #1284

---

2025 年我们已经支持的服务商有：

• LM Studio: by @arvinxx
  • ✨ feat: add lm studio #4483
• Doubao: Thanks to @sxjeru
  • ✨ feat: Support Doubao Models #5481
  • ✨ feat: Support Doubao Models #3055
• TencentCloud: by @arvinxx
  • ✨ feat: support tencent cloud #6029
• Nvidia NIM Thanks to @hezhijie0327
  • ✨ feat: add Nvidia NIM provider support #6142
• vLLM Thanks to @hezhijie0327
  • ✨ feat: add vLLM provider support #6154
• Jina AI Thanks to @hezhijie0327
  • ✨ feat: add Jina AI model provider support #6140
• PPIO Thanks to @cnJasonZ
  • ✨ feat: add new model provider PPIO #6133
• Azure AI by @arvinxx
  • ✨ feat: add Azure AI as new Provider #6214
• Google Vertex AI: by @arvinxx
  • ✨ feat: support vertex ai #4487
• SambaNova Thanks to @hezhijie0327
  • ✨ feat: add SambaNova provider support #6218
• 火山引擎 by @arvinxx
  • ✨ feat: add volcengine as a new provider #6221

Plan：

Important

If you have any requests for new model suppliers, feel free to comment below. When the number of upvotes exceeds 15, we will consider implementing it.

如果大家对于新模型供应商有诉求，欢迎在下方跟帖，当up数超过 15 时，我们会考虑将其实现

---

PRs Welcome 💞

• A demo PR of add OpenAI Compatible Provider: ✨ feat: add lm studio #4483

Tip

We also welcome PRs. We have received many contributions regarding model Providers, so we have maintained a library of icons for LLMs and Provider vendors, facilitating everyone's future development. https://github.com/lobehub/lobe-icons

同时欢迎 PR，我们已经收获到许多关于模型 Provider 的贡献, 因此我们维护了一个 LLMs 和 Provider 供应商的图标库，方便大家后续开发 https://github.com/lobehub/lobe-icons

[2247ds]

求支持ModelScope，OpenAI API兼容
https://modelscope.cn/docs/model-service/API-Inference/intro

[arvinxx]

ModelScope 不是 Qwen 吗？

[2247ds]

qwen是百炼吧，我百炼的api是填qwen里用的。
百炼跟魔搭算是一家公司的两个产品？

[arvinxx]

这样啊 了解了

[black-zero358]

请求支持华为云下的ModelArts Studio

[xccado]

求支持华为云ModelArts Studio，兼容OpenAi API，通过openai api的代理地址和key可以使用，不过会频繁跳出错误。
https://support.huaweicloud.com/usermanual-maas-modelarts/maas-modelarts-0011.html
不过他的api调用好像有点麻烦，每个模型的接口地址都不一样

[hpeiyan]

luchentech and infini-ai. Please!

[zhaozhihua97]

为什么1.15.9的版本里还是看不到volcengine的设置项呢？

[hension-code]

其实完全弄一个添加自定义模型的选项（兼容OPENAI），在里面可以配置URL、APIKEY、TOKEN、MODEL这些信息，然后再加一个多选项：推理、附件上传、图片生成之类的，这句选项提供服务

[black-zero358]

支持采取这种方法