xiaohei
428644e286
Revalidate Docs / Revalidate Docs (push) Failing after 2s
E2E CI / Check Duplicate Run (push) Failing after 5s
Test CI / Check Duplicate Run (push) Failing after 6s
E2E CI / Test Web App (push) Has been skipped
Test CI / Test Packages (push) Has been skipped
Test CI / Test App (shard 1/3) (push) Has been skipped
Test CI / Test App (shard 2/3) (push) Has been skipped
Test CI / Test App (shard 3/3) (push) Has been skipped
Test CI / Test Desktop App (push) Has been skipped
🔄 Branch Synchronization / sync-branches (push) Failing after 11s
Test CI / Test Database (push) Has been skipped
Test CI / Merge and Upload App Coverage (push) Has been skipped
Database Schema Visualization CI / build (push) Failing after 4m14s
70 lines
3.0 KiB
Plaintext
70 lines
3.0 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
|
|
- ChatGLM
|
|
- 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-4o, o1), 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** — DALL-E 3, fal.ai, BFL, 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'} />
|