PrboChat
PrboChat
Discover
Ctrl
K
Back to Discovery
ModelScopeModelScope
@ModelScope
5 models
modelscope.description

Supported Models

ModelScope
DeepSeek

DeepSeek-R1-0528

deepseek-ai/DeepSeek-R1-0528
128K
Maximum Context Length
128K
Maximum Output Length
--
Input Price
--
Output Price
--
DeepSeek

DeepSeek-V3

deepseek-ai/DeepSeek-V3
128K
Maximum Context Length
128K
Maximum Output Length
--
Input Price
--
Output Price
--
DeepSeek

DeepSeek R1

deepseek-ai/DeepSeek-R1
128K
Maximum Context Length
128K
Maximum Output Length
--
Input Price
--
Output Price
--
Qwen

Qwen3-235B-A22B

Qwen/Qwen3-235B-A22B
128K
Maximum Context Length
128K
Maximum Output Length
--
Input Price
--
Output Price
--

ModelScope Provider Setup

ModelScope (魔塔社区) is Alibaba's open-source model community that provides access to various AI models. This guide will help you set up the ModelScope provider in LobeChat.

Prerequisites

Before using ModelScope API, you need to:

  1. Create a ModelScope Account

  2. Bind Alibaba Cloud Account

    • Important: ModelScope API requires binding with an Alibaba Cloud account
    • Visit your ModelScope Access Token page
    • Follow the instructions to bind your Alibaba Cloud account
    • This step is mandatory for API access

  3. Get API Token

    • After binding your Alibaba Cloud account, generate an API token
    • Copy the token for use in LobeChat

Configuration

Environment Variables

Add the following environment variables to your .env file:

bash
# Enable ModelScope provider
ENABLED_MODELSCOPE=1

# ModelScope API key (required)
MODELSCOPE_API_KEY=your_modelscope_api_token

# Optional: Custom model list (comma-separated)
MODELSCOPE_MODEL_LIST=deepseek-ai/DeepSeek-V3-0324,Qwen/Qwen3-235B-A22B

# Optional: Proxy URL if needed
MODELSCOPE_PROXY_URL=https://your-proxy-url

Docker Configuration

If using Docker, add the ModelScope environment variables to your docker-compose.yml:

yaml
environment:
  - ENABLED_MODELSCOPE=1
  - MODELSCOPE_API_KEY=your_modelscope_api_token
  - MODELSCOPE_MODEL_LIST=deepseek-ai/DeepSeek-V3-0324,Qwen/Qwen3-235B-A22B

Available Models

ModelScope provides access to various models including:

  • DeepSeek Models: DeepSeek-V3, DeepSeek-R1 series
  • Qwen Models: Qwen3 series, Qwen2.5 series
  • Llama Models: Meta-Llama-3 series
  • Other Models: Various open-source models

Troubleshooting

Common Issues

  1. "Please bind your Alibaba Cloud account before use" Error

    • This means you haven't bound your Alibaba Cloud account to ModelScope
    • Visit ModelScope Access Token page
    • Complete the Alibaba Cloud account binding process

  2. 401 Authentication Error

    • Check if your API token is correct
    • Ensure the token hasn't expired
    • Verify that your Alibaba Cloud account is properly bound

  3. Model Not Available

    • Some models may require additional permissions
    • Check the model's page on ModelScope for access requirements

Debug Mode

Enable debug mode to see detailed logs:

bash
DEBUG_MODELSCOPE_CHAT_COMPLETION=1

Notes

  • ModelScope API is compatible with OpenAI API format
  • The service is primarily designed for users in China
  • Some models may have usage limitations or require additional verification
  • API responses are in Chinese by default for some models

Support

For ModelScope-specific issues:

For LobeChat integration issues:

Related Providers

OpenAIOpenAI
@OpenAI
24 models
OpenAI is a global leader in artificial intelligence research, with models like the GPT series pushing the frontiers of natural language processing. OpenAI is committed to transforming multiple industries through innovative and efficient AI solutions. Their products demonstrate significant performance and cost-effectiveness, widely used in research, business, and innovative applications.
OllamaOllama
@Ollama
45 models
Ollama provides models that cover a wide range of fields, including code generation, mathematical operations, multilingual processing, and conversational interaction, catering to diverse enterprise-level and localized deployment needs.
Anthropic
ClaudeClaude
@Anthropic
11 models
Anthropic is a company focused on AI research and development, offering a range of advanced language models such as Claude 3.5 Sonnet, Claude 3 Sonnet, Claude 3 Opus, and Claude 3 Haiku. These models achieve an ideal balance between intelligence, speed, and cost, suitable for various applications from enterprise workloads to rapid-response scenarios. Claude 3.5 Sonnet, as their latest model, has excelled in multiple evaluations while maintaining a high cost-performance ratio.
AWS
BedrockBedrock
@Bedrock
17 models
Bedrock is a service provided by Amazon AWS, focusing on delivering advanced AI language and visual models for enterprises. Its model family includes Anthropic's Claude series, Meta's Llama 3.1 series, and more, offering a range of options from lightweight to high-performance, supporting tasks such as text generation, conversation, and image processing for businesses of varying scales and needs.
Google
GeminiGemini
@Google
12 models
Google's Gemini series represents its most advanced, versatile AI models, developed by Google DeepMind, designed for multimodal capabilities, supporting seamless understanding and processing of text, code, images, audio, and video. Suitable for various environments from data centers to mobile devices, it significantly enhances the efficiency and applicability of AI models.