2024 Model Providers support | 2024 年模型服务商支持

[arvinxx]

2025 support:

• 2025 AI Provider Support | 2025 年 AI 服务商支持 #6157

---

LobeChat currently supports many model providers, and considering the development of the AI ecosystem, we have specifically opened this discussion to record everyone's needs for new model service providers.

LobeChat 目前已经支持了诸多模型供应商，考虑到 AI 生态的发展，我们专门开放此贴用于记录大家对于新模型服务商的需求。

---

Currently, the service providers currently supported by LobeChat are as follows:

目前 LobeChat 已支持的服务商如下：

• OpenAI
• Azure OpenAI
  • ✨ feat: support Azure OpenAI #177
• AWS Bedrock
  • ✨ feat: support Google / Zhipu / AWS Bedrock model providers #1173
  • Claude3: ✨ feat: add claude 3 to bedrock provider #1551
• Google Model （Gemini Pro 、Gemini Pro Vision）
  • ✨ feat: support Google / Zhipu / AWS Bedrock model providers #1173
  • Gemini 1.5 pro: 🐛 fix: fix Google Gemini pro 1.5 and system role issue #1801
• Zhipu AI (智谱AI)
  • ✨ feat: support Google / Zhipu / AWS Bedrock model providers #1173
• Moonshot AI (月之暗面) by @arvinxx
  • ✨ feat: support Moonshot AI #1232
• Ollama (Local LLM) Thanks to @sjy
  • ✨ feat(llm): support Ollama AI Provider (local llm) #1265
• Perplexity AI Thanks to @gijigae
  • ✨ feat: support the perplexity provider #1339
• Anthropic Thanks to @danielglh
  • ✨ feat: support anthropic as model provider #1409
• Mistral Thanks to @danielglh
  • ✨ feat: support mistral as model provider #1455
• Groq Thanks to @jcdiv47 and @pzcn
  • ✨ feat: add support for model provider Groq #1562
  • Add Groq localization #1570
  • ✨ feat: support model provider groq #1569
• OpenRouter: Thanks to @danielglh
  • ✨ feat: support openrouter as a new model provider #1572
• 01.AI（零一万物）: Thanks to @MapleEve
  • ✨ feat: support 01.AI as a new provider #1627
• TogetherAI: Thanks to @phsontung
  • ✨ feat: Support TogetherAI as new model provider #1709
• MiniMax Thanks to @lwshen
  • ✨ feat: support minimax as provider #2087
• DeepSeek: Thanks to @RubuJam
  • ✨ feat: Support DeepSeek as new model provider #2446
  • 🐛 fix: fix DeepSeek using wrong model ID #2484
• Qwen: Thanks to @justmywyw
  • ✨ feat: Support Qwen as new model provider #2715
• Stepfun(阶跃星辰)： by @arvinxx
  • 💄 style: add stepfun as a new provider #2803
• Baichuan (百川）： Thanks to @hezhijie0327
  • ✨ feat: Add Baichuan model provider #3097
• Taichu(太初): Thanks to @hezhijie0327
  • ✨ feat: Add Taichu model provider #3129
• 360 AI（360智脑） : Thanks to @hezhijie0327
  • ✨ feat: Add 360AI model provider #3130
• Novita AI: Thanks to @jasonhp
  • 💄 style: Add new model provider Novita AI #3177
• SiliconCloud: Thanks to @sxjeru
  • ✨ feat: Add SiliconCloud model provider #3092
• Fireworks AI Thanks to @hezhijie0327
  • ✨ feat: Add Fireworks AI Model Provider #3392
• Spark (讯飞星火): Thanks to @hezhijie0327
  • ✨ feat: Add Spark model provider #3098
• Github Models: Thanks to @CloudPassenger
  • ✨ feat: add Github Models provider #3869
• AI21 Labs: Thanks to @hezhijie0327
  • ✨ feat: add Ai21Labs model provider #3727
• Tencent Hunyuan(腾讯混元): Thanks to @hezhijie0327
  • ✨ feat: add Hunyuan(Tencent) model provider #4147
• Wenxin(文心一言): by @arvinxx
  • ✨ feat: add wenxin as a new provider #2802
  • ✨ feat: add wenxin model provider #4018
• Hugging Face Inference API: by @arvinxx
  • ✨ feat: add HuggingFace Model Provider #4225
• SenseNova: Thanks to @hezhijie0327
• ✨ feat: add SenseNova (商汤) model provider #4162
• Cloudflare AI: Thanks to @BrandonStudio , @sxjeru
  • ✨ feat: Support Cloudflare Workers AI #3402
  • ✨ feat: Support Cloudflare Workers AI #2966
• xAI : Thanks to @hezhijie0327
  • ✨ feat: add support xAI provider #4627
• InternLM: Thanks to @hezhijie0327
  • ✨ feat: add support InternLM (书生浦语) provider #4711
• Gitee AI: Thanks to @hezhijie0327
  • ✨ feat: add Gitee AI model provider #4716

WIP：

• Cohere : Thanks to @ystoneman
  • Add initial implementation for Cohere provider support #2539

Plan：

• replicate

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

[lesonky]

申请增加GCP的Vertex AI大模型服务，此类服务用服务账号身份认证。可以满足企业级数据合规要求。🙏

[arvinxx]

the upvote is more than 8, we will add Google Vertex AI Soon.

[AiharaMahiru]

There are still fewer API providers that offer the Claude family of models, I've used AWS before as a Claude API, but asking me to provide sensitive data such as credit card statements is unacceptable!

[ViktorJJF]

I would like Vertex AI in Lobechat too pleasee

[J4gQBqqR]

Could you please add deepinfra and enable function calling for this provider?
Deepinfra has the cheapest rate per token across all providers.
Thanks.

[freechw]

希望可以增加GPUStack，GPUStack支持多机集群式部署，统一管理，支持linux，windows，mac系统，支持Nvidia，AMD，摩尔线程，华为等多种GPU和CPU进行推理。支持LLM，图像生成，STT，TTS，embedding，reranker大模型，API与OpenAI兼容。

[muyuanjin]

希望添加 hyperbolic，hyperbolic 的 deepseek-r1 是目前长上下文里性价比最高的供应商 131k Context $2.00 / 1M tokens

[Cchongdada]

希望能添加volcengine（火山方舟）

[arvinxx]

@sxjeru 要不要考虑把豆包重名为火山引擎呢

[tanpengsccd]

或者 “字节 豆包/火山”

[Starlitnightly]

目前在 lobechat，豆包就是火山方舟。

如果不是服务端数据库版本，请在环境变量添加 NEXT_PUBLIC_CLIENT_DB=pglite 以启用豆包。

另外豆包的模型配置请使用环境变量 DOUBAO_MODEL_LIST 参考 Azure 的 https://lobehub.com/zh/docs/self-hosting/examples/azure-openai#%E5%9C%A8%E9%83%A8%E7%BD%B2%E6%97%B6%E9%85%8D%E7%BD%AE

最关键的是“部署名”要填对，即火山方舟的在线推理终结点（ep-xxx）

不行，会报错：

{
  "error": {
    "code": "MissingParameter",
    "message": "The request failed because it is missing one or multiple required parameters. Request id: 02173926983665960c2c73c0b81f55170035a889a417d644d32f1",
    "param": "",
    "type": "BadRequest"
  },
  "endpoint": "https://ark.cn-beijing.volces.com/api/v3",
  "provider": "doubao"
}

部署的时候docker run的是：

  -e DOUBAO_MODEL_LIST=DeepSeek-R1>ep-20250211160940-rgsn6=DeepSeek-R1 \
  lobehub/lobe-chat-database

[BertramRay]

目前在 lobechat，豆包就是火山方舟。
如果不是服务端数据库版本，请在环境变量添加 NEXT_PUBLIC_CLIENT_DB=pglite 以启用豆包。
另外豆包的模型配置请使用环境变量 DOUBAO_MODEL_LIST 参考 Azure 的 https://lobehub.com/zh/docs/self-hosting/examples/azure-openai#%E5%9C%A8%E9%83%A8%E7%BD%B2%E6%97%B6%E9%85%8D%E7%BD%AE
最关键的是“部署名”要填对，即火山方舟的在线推理终结点（ep-xxx）

不行，会报错：

{
  "error": {
    "code": "MissingParameter",
    "message": "The request failed because it is missing one or multiple required parameters. Request id: 02173926983665960c2c73c0b81f55170035a889a417d644d32f1",
    "param": "",
    "type": "BadRequest"
  },
  "endpoint": "https://ark.cn-beijing.volces.com/api/v3",
  "provider": "doubao"
}

部署的时候docker run的是：

  -e DOUBAO_MODEL_LIST=DeepSeek-R1>ep-20250211160940-rgsn6=DeepSeek-R1 \
  lobehub/lobe-chat-database

DOUBAO_MODEL_LIST=+ep-20250211160940-rgsn6
和你遇到了一样的报错，你可以把变量改成这样
r1也能显示思维链内容

[Starlitnightly]

不好意思打扰一下，我部署的代码如下，省略了auth0和cloudfare的R2桶，修改成你给的代码后，依然报错，想问一下你是运行lobechat的时候加的参数吗？还是运行的lobe-chat-database 加的参数？

谢谢

docker run -it -d --name lobe-chat-database -p 3210:3210 \
  -e DATABASE_URL=postgres://postgres:[email protected]:5432/postgres \
  -e S3_BUCKET=lobechat \
  -e S3_PUBLIC_DOMAIN=https://omicverse.com \
  -e DOUBAO_MODEL_LIST=+ep-20250211160940-rgsn6 \
  lobehub/lobe-chat-database

[FishYY1989]

Wish to add vllm，https://docs.vllm.ai/en/latest/getting_started/quickstart.html

[anyu5733]

请问如何自建。在语言模型-OpenAI项下 API Key API 代理地址填入对应信息，模型列表也自定义模型配置后，检查依旧失败。提示如下：
{
"error": {
"message": "invalid model",
"type": "runtime_error",
"param": null,
"code": "20033"
},
"endpoint": "https://api.lkeap.cloud.te****nt.com/v1",
"provider": "openai"
}

[sxjeru]

检查一下模型名是否有误？
https://docs.vllm.ai/en/v0.6.2/models/supported_models.html

[anyu5733]

自定义模型配置中的 模型 ID 模型展示名称 两项都以改为对应名称。该模型名称使用脚本可正确访问.
deepseek-r1
https://api.lkeap.cloud.tencent.com/v1

[arvinxx]

@sxjeru 感觉可以考虑把vllm 加一个本地部署的版本，就像lm studio一样

[arvinxx]

1.55.0 have supported vLLM #6154

[BertramRay]

感觉现在在配置中配置，自行新建类 openai 提供商以及新增模型，并不能指定该模型是否具备reasoning, vision, function_calling能力，这个能否后续配置化呢？
比如火山方舟的推理点（类似ep-20250207185449-q56n6）根本看不出是什么模型，但实际上他是r1，应该启用reasoning展示思维链
不太了解这一块为什么没有通用配置化，是openai的协定，各家模型云供应商没有好好遵循，导致必须针对性的去开发吗

[sxjeru]

所以才会有部署名的设置，所有与模型相关的信息都跟随模型 id，而请求的模型名则是部署名（deployName）。

[yanfeng1022]

是否可以提供mindscope提供的接口，是与openai兼容的接口
https://modelscope.cn/docs/model-service/API-Inference/intro

[Nick17t]

Hi Lobe-chat team,
thanks for the great design and quick updates! we're launching jina-deepsearch-v1, a new reasoning+search LLM API. more info

We'd like to propose it as a native built-in provider. It's already working as a 3rd-party integration, and it's OpenAI compatible, native integration should be easy. guidelines :)

[SAnBlog]

Hi Lobe-chat team,  您好 Lobe-chat 团队， thanks for the great design and quick updates! we're launching jina-deepsearch-v1, a new reasoning+search LLM API. more info感谢你们的出色设计和快速更新！我们正在推出 jina-deepsearch-v1 ，一个新的推理 + 搜索 LLM API。更多信息

We'd like to propose it as a native built-in provider. It's already working as a 3rd-party integration, and it's OpenAI compatible, native integration should be easy. guidelines :)我们想将其作为本机内置提供程序提出。它已经作为第 3 方集成工作，并且与 OpenAI 兼容，原生集成应该很容易。准则 :)

返回的格式要适配一下

[Nick17t]

感谢快速回复，我们这边已经适配好了。

[arvinxx]

here is the PR: #6140. And I'm working on the jina icon in the lobe-icons.

[arvinxx]

@Nick17t jina-deepsearch-v1 的 contextWindowsToken 等信息有吗？在哪能看到？

[easeyang]

Cherrystudio 上能自己配置供应商的模型，这个功能能跟进吗？毕竟供应商都提供了兼容openai的接口

[sxjeru]

• 自己部署的Lobe版本，新的AI Provider无法展示，仍然是老版本的视图 #5865

等 pglite 全面铺开就能享受自定义供应商的功能了。

[Thelast0802]

您好！首先感谢LobeChat团队开发了如此高效且易用的开源工具，社区版的Vercel一键部署功能极大地降低了使用门槛。

在此想提出一个功能建议：能否在社区版本（尤其是Vercel部署场景）中增加对「火山方舟」模型服务商的支持？

理由如下：
1️⃣ 多样性提升：火山方舟提供多个国产大模型（如豆包、云雀等），可丰富中文场景的对话和语义理解能力。
2️⃣ 成本优势：其按量付费模式对个人开发者/小规模项目更友好，适合社区版用户灵活尝试。
3️⃣ 合规适配：火山引擎的境内节点和资质，可能满足部分用户对数据合规性的需求。

若技术实现可行，这将成为社区版差异化的重要亮点。如果需要相关测试或文档协助，我愿意提供支持！

再次感谢团队的辛勤付出，期待LobeChat生态越来越强大！

[geek-mr-xie]

我也觉得应该添加火山engine，豆包pro模型还可以，有希望

[arvinxx]

火山方舟和火山引擎有啥区别？

[sxjeru]

火山引擎 类似 阿里云，是综合性云服务商。其提供的大模型服务全称是“火山方舟大模型服务平台”，简称火山方舟，类似于阿里云的“百炼”。

[arvinxx]

@sxjeru 豆包那个我准备不动，加个标记准备废弃了。后面就换成火山方舟好了

[xccado]

能否添加华为云和硅基流动

[arvinxx]

硅基流动已经有了，华为云是哪个