mirror of
https://github.com/lobehub/lobehub.git
synced 2026-09-20 04:56:13 +08:00
YuTengjing
191f3fe776
* 📝 docs: fix outdated content across the docs site Audited docs/ against the current codebase and fixed stale content that drifted after major refactors (Clerk/NextAuth → Better Auth, src/server → apps/server, src/{config,envs,locales} → packages/*, model-bank updates). - self-hosting/auth: mark removed NextAuth/Clerk pages with deprecation warnings; fix microsoft/zitadel alias claims and the Logto callback path - environment-variables & advanced: correct wrong defaults (S3_SET_ACL, AI_IMAGE_DEFAULT_IMAGE_NUM, index/proxy URLs), drop non-existent env vars and fictional feature flags, fix OIDC config guidance - development: update refactored paths, Better Auth, .mjs configs, remove the MSW section (msw is not a dependency) - providers & model examples: replace retired model ids with in-bank ones; fix comfyui frontmatter corruption - usage: rename Moderator→Orchestrator, GTD→Task, correct shortcut keys, channel capability tables, Feishu/Lark WebSocket mode - platform/migration: fix dead links, docker service name, npx/npm → bun EN and zh-CN pairs updated together. * 📝 docs: fix Logto callback path and AUTH_SECRET deprecation guidance - Revert Logto/Sealos callback URLs to /api/auth/callback/logto to match the runtime SSO redirectURI override - Narrow legacy auth Callout: AUTH_SECRET remains required for Better Auth; mark NEXT_AUTH_SECRET as deprecated in zh-CN * 📝 docs: refresh agent skills for locales, env, auth, and agentRun paths Align OSS agent guidance with post-refactor layout: - packages/locales/src/default + bun run i18n - packages/env/src for env schemas (@/envs alias) - spa-auth shell + src/routes/auth segments - chat agentRun/transports/hetero instead of aiChat * 📝 docs: document APP_URL as required for Better Auth base URL Self-hosted auth uses appEnv.APP_URL as baseURL, not request-header auto-detection. NEXT_PUBLIC_AUTH_URL remains deprecated. * 📝 docs: note self-host search provider setup for web search Built-in lobe-web-browsing needs no client plugin, but self-hosted servers still require SEARCH_PROVIDERS / SEARXNG_URL (default SearXNG). * 📝 docs: point feature guide welcome UI at AgentHome Opening message/questions on the agent chat page live in src/features/AgentHome, not Onboarding WelcomeMessage.
70 lines
3.1 KiB
Plaintext
70 lines
3.1 KiB
Plaintext
---
|
|
title: Using Multiple Model Providers in LobeHub
|
|
description: >-
|
|
Learn about the latest developments in LobeHub's support for multiple model
|
|
providers, including currently supported providers, planned expansions, and
|
|
how to use local models.
|
|
tags:
|
|
- LobeHub
|
|
- AI Chat Services
|
|
- Model Providers
|
|
- Multi-Model Support
|
|
- Local Model Support
|
|
- AWS Bedrock
|
|
- Google AI
|
|
- Zhipu
|
|
- Moonshot AI
|
|
- 01 AI
|
|
- Together AI
|
|
- Ollama
|
|
---
|
|
|
|
# Using Multiple Model Providers in LobeHub
|
|
|
|
<Image alt={'Multi-Model Provider Support'} borderless cover src={'/blog/assets17870709/1148639c-2687-4a9c-9950-8ca8672f34b6.webp'} />
|
|
|
|
As LobeHub continues to evolve, we've come to deeply understand the importance of supporting a diverse range of model providers to meet the needs of our community. Rather than relying on a single provider, we've expanded our support to include multiple AI model services, offering users a richer and more versatile chat experience.
|
|
|
|
## Why Multi-Provider Support?
|
|
|
|
LobeHub's multi-provider architecture offers several key advantages:
|
|
|
|
- **Unified intelligence** — Access any model and any modality from a single interface
|
|
- **Cost optimization** — Switch between providers to optimize for performance and budget
|
|
- **Vendor independence** — Avoid lock-in and maintain service continuity if one provider has downtime
|
|
- **Flexibility** — Mix and match models for different agents and use cases
|
|
- **Local option** — Use Ollama or LM Studio for complete data privacy and no API costs
|
|
|
|
## Provider Categories
|
|
|
|
LobeHub integrates with 70+ AI model providers:
|
|
|
|
- **Major commercial** — OpenAI (GPT-5, o3), Anthropic (Claude), Google (Gemini), Microsoft Azure OpenAI, AWS Bedrock
|
|
- **Inference platforms** — OpenRouter, Together AI, Groq, Fireworks AI, SambaNova
|
|
- **Chinese providers** — Zhipu, Moonshot, DeepSeek, Baichuan, Qwen (Alibaba), Wenxin (Baidu), Spark (iFlytek)
|
|
- **Local models** — Ollama, LM Studio (no API costs, complete privacy, offline capability)
|
|
- **Image generation** — GPT Image, Flux, Seedream, Imagen, ComfyUI
|
|
|
|
## Setting Up Providers
|
|
|
|
Each provider is configured in **Settings → Language Model**:
|
|
|
|
1. Select the provider from the list
|
|
2. Enter your API key (from the provider's developer console)
|
|
3. Optionally set a custom base URL if using a proxy or self-hosted endpoint
|
|
4. Save and select a model to start chatting
|
|
|
|
For environment variable configuration in self-hosted deployments, see the [model provider environment variables](/docs/self-hosting/environment-variables/model-provider) reference.
|
|
|
|
## Troubleshooting
|
|
|
|
**Connection error / API key invalid** — Double-check your API key for extra spaces. Ensure you're using the correct key type for the provider.
|
|
|
|
**Model not available** — The model may not be included in your account tier or may have been deprecated. Check the provider's model availability page.
|
|
|
|
**Rate limit errors** — You've hit the provider's request rate limit. Consider distributing requests across multiple providers, or upgrade your account tier.
|
|
|
|
## How to Use Model Providers
|
|
|
|
<ProviderCards locale={'en'} />
|