Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.agipower.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Guide to Using Cherry Studio via AGIPower

Cherry Studio is an elegant cross-platform AI desktop client that supports multiple mainstream large language model services. Through integration with AGIPower, you can access the extensive model catalog aggregated on the AGIPower platform within Cherry Studio, enjoying more flexible model selection and better pricing.
AGIPower fully supports the OpenAI Chat Completions protocol and can be seamlessly integrated into clients like Cherry Studio that support custom OpenAI-compatible endpoints. Simply add AGIPower as a model provider to use all models that support the OpenAI protocol.Note that the base_url for the OpenAI protocol is https://api.agipower.ai/v1/.

​
Configuration

​
Step 1: Download and Install Cherry Studio

Go to the Cherry Studio official site to download the version for your operating system and complete the installation.

​
Step 2: Add the AGIPower Model Provider

  1. Open Cherry Studio and go to the Settings → Model Provider page
  2. Click the Add button to add a new model provider
  3. Fill in the following details in the configuration dialog:
    • Provider Name: AGIPower (or any preferred name)
    • Provider Type: select OpenAI
    • API Key: enter your AGIPower API Key (format sk-xxx)
    • API Host: https://api.agipower.ai/v1/
Add AGIPower Provider Fill in Provider Details Fetch Model List
Make sure to replace sk-xxx with your actual AGIPower API Key. You can obtain your API Key from the AGIPower Console.
  • Provider Name: Customizable; using AGIPower is recommended for clarity
  • Provider Type: Must select OpenAI, as AGIPower supports the OpenAI Chat Completions protocol
  • API Key: Your AGIPower API Key for authentication and billing
  • API Host: AGIPower’s OpenAI-compatible endpoint address; must end with /

​
Step 3: Fetch the Available Model List

After configuration, click the Manager button. Cherry Studio will automatically fetch the list of all models that support the OpenAI Chat Completions protocol from AGIPower.
Cherry Studio will automatically discover all available models via AGIPower’s /v1/models API endpoint—no manual addition required.

​
Step 4: Add the Models You Need

From the fetched model list, select the models you want to use and add them to your model library. Add Models
We recommend adding models across different capability and price tiers to suit various use cases:
  • High-performance models: openai/gpt-5, anthropic/claude-sonnet-4.5
  • Balanced models: google/gemini-2.5-pro, x-ai/grok-4-fast
  • Cost-effective models: deepseek/deepseek-chat, qwen/qwen3-coder-plus

​
Step 5: Start a Conversation

Go to the chat interface, select any model under the AGIPower provider, and start using it. Select a Model to Start Chatting
You can switch between models at any time during a conversation. Cherry Studio preserves the chat history, making it easy to compare outputs from different models.

​
Supported Models

AGIPower offers a large and constantly growing set of models that support the OpenAI Chat Completions protocol. You can view the full list in the following ways:
  • Visit the AGIPower Model List and filter by “OpenAI API Compatible”
  • Or visit the detail page of a specific model to check its protocol support
Visit the AGIPower Model List to learn about all available models and their details, including pricing, context length, feature capabilities, and more.

​
Usage Experience

Once configured, you can seamlessly use a variety of AGIPower models within Cherry Studio:
  • Unified chat interface without switching between different clients
  • Real-time model switching to compare output quality
  • Complete chat history management and export
  • Advanced features such as file uploads and multimodal input
Feature support varies across models, such as visual understanding and function calling. Refer to the detail page of each model for its capabilities.

​
Troubleshooting

​
Common Issues

​
API Key Error

Issue: Invalid or unauthorized API Key when adding a provider Solutions:
  • Check if the API Key was copied correctly; avoid extra spaces or line breaks
  • Confirm the API Key format starts with sk-
  • Verify the API Key is activated and the account has sufficient balance
  • Log in to the AGIPower Console to check the API Key status

​
Unable to Fetch Model List

Issue: Unable to retrieve the model list after clicking the Manager button Solutions:
  • Check if the API Host is correctly set to https://api.agipower.ai/v1/ (note the trailing slash)
  • Verify network connectivity and try accessing https://agipower.ai in your browser
  • Ensure firewall or proxy settings are not blocking access to the AGIPower servers
  • Check whether your Cherry Studio version is up to date; older versions may have compatibility issues

​
Model Invocation Failed

Issue: Errors returned after selecting a model and sending a message Solutions:
  • Confirm the selected model is still available on the AGIPower platform (some models may be retired)
  • Check whether your account balance is sufficient
  • Verify that the model supports your request parameters (e.g., temperature, max_tokens, etc.)
  • Review the detailed error message and adjust request parameters accordingly
  • Try switching to another model to determine if the issue is specific to a particular model

​
Slow Response

Issue: Model responses are slow or lagging Solutions:
  • Check your network quality and diagnose with a speed test tool
  • Try switching to a model labeled “fast” (e.g., x-ai/grok-4-fast)
  • Reduce the token count per request by lowering the max_tokens parameter
  • Avoid peak usage periods or select models with lower load
  • If the issue persists, contact AGIPower technical support for assistance
If you encounter any issues during use or have suggestions and feedback, feel free to reach us via:For more contact options and details, please visit our Contact Us page.