Cherry Studio × AI Code With
Cherry Studio third-party API / relay setup tutorial
Use the AI Code With OpenAI-compatible API inside the Cherry Studio desktop client. Add a custom provider, enter your API key and the API address, and you can use DeepSeek, Gemini, GLM, Kimi, and more models directly in Cherry Studio. This page covers the setup steps, common errors, and FAQ.
Download and install Cherry Studio first, then add the AI Code With custom provider in Settings; the API key is only entered in Cherry Studio, never on this page.
- Provider Name
- AI Code With
- API Address
- https://api.aicodewith.ai/v1
- API Key
- sk-xxxxxxxx
- Model
- deepseek-v4-flash
Quick setup
Follow the 3 steps below to install, add a custom provider, and send a test message — about 3 minutes.
Cherry Studio is a desktop AI client that supports custom providers. Fill in the fields, copy values, and verify in the 3 steps below.
Download and install Cherry Studio
Download the installer for your platform (Windows, macOS, or Linux) from the official page and install it. Launch Cherry Studio and complete the first-run setup.
Add AI Code With as a custom provider
Open Settings and go to Model Services. Select New API in the provider list (or click Add provider at the bottom), then enable the toggle. Paste your AI Code With API key (it stays on your machine) and set the API address to https://api.aicodewith.ai/v1. You can click Check first to confirm the connection.
In Settings → Model Services, select New API, enter your API key and the API address https://api.aicodewith.ai/v1. Enable the toggle, then use Check and Sync models. Add a model and verify
Click Sync models to fetch available models, or click + and type a Model ID. Then start a new conversation, pick that model, and send a test message. A normal reply from the selected model means the setup works — match the call by time and model in AI Code With usage records. Do not treat a reply from the built-in Feedback assistant as a successful connection.
Recommended models
After adding the provider, click Sync models to fetch models automatically, or click + and type one of these Model IDs (recommended models are selected by default and ready to copy):
1 selected
Claude
GPT
Gemini
DeepSeek
GLM
Kimi
The full model list follows the AI Code With docs and pricing page; this site does not maintain a separate model list.
After Sync models, add the models you need. The full list follows what this account can see. Then start a new chat, pick that model, send a test message, and match the call in AI Code With usage records.
How it works
Cherry Studio stores the custom provider in local settings. When you send a message, the request goes through the OpenAI-compatible endpoint to AI Code With, then to the selected model. Provider Name, API Key, and API Address belong in Quick setup above — this section only explains the path.
- Desktop client
- Cherry Studio owns the chat UI, model picker, and local config. No plugin and no config file.
- Custom provider
- One OpenAI-compatible provider entry that points Cherry Studio at AI Code With instead of an official model vendor.
- Request path
- Cherry Studio → custom provider → API Address → model. Changing the model does not rewrite the saved API address.
Fields, copy actions, and verification live in Quick setup. This section only explains how a request reaches the model.
Frequently asked questions
What plugin do I need to use AI Code With in Cherry Studio?
None. Cherry Studio is a desktop client — in Settings → Model Services, select New API, then enter the API address https://api.aicodewith.ai/v1 plus your AI Code With API key.
What should I enter as the API address?
Enter https://api.aicodewith.ai/v1. In Settings → Model Services, select New API and put that address in the API address field. Keep the /v1 suffix and do not append extra paths like /v1/models.
What if I can't fetch the model list?
If Sync models returns nothing, click + and type a Model ID manually (for example, deepseek-v4-flash). Save, and the model becomes selectable in the chat view.
Where do I get the API key?
Create an API key in the AI Code With dashboard under Key Management. The key is shown only once, so save it carefully, then paste it in the Cherry Studio provider settings.
How do I confirm the setup works?
Enable the provider toggle, start a new conversation, pick the model you just added, and send a message. Only a reply from that model counts as success — do not treat the built-in Feedback assistant as a successful connection. Then match the call by time and model in AI Code With usage records.
Don't have Cherry Studio installed?
Download the Windows, macOS, or Linux build from the Cherry Studio website and install it.
Cherry Studio official download
Visit the official download page and pick the installer for your platform. Supported platforms: Windows, macOS (Intel and Apple Silicon), and Linux (x86_64 and ARM64).
Download from the official pageFull install guidance follows the Cherry Studio official docs; this site does not host or modify installers.
Common error troubleshooting
The most frequent problems fall into 4 categories.
401 / Invalid API Key
Symptom: The request returns 401, Unauthorized, or Invalid API Key.
Cause: Usually the API key is invalid, mistyped, or copied with extra characters.
- Re-paste the API key in the Cherry Studio provider settings (no extra spaces)
- Confirm the key is a valid AI Code With API key
- Retry sending a message
Model Not Found / Wrong Model ID
Symptom: The request reports Model Not Found or an unknown model.
Cause: The Model ID is mistyped, or the model is currently unavailable.
- Check the Model ID in the provider settings matches the one on this page
- Confirm the key can access that model
- Confirm the model is available on the AI Code With pricing page
API address error
Symptom: The request fails on test or when sending a message, or the model list is empty.
Cause: The API Address has a wrong path, or /v1 is missing.
- Confirm the value is https://api.aicodewith.ai/v1 (with /v1)
- Remove any trailing /v1/models or guessed path
- Save the settings and test again
Sync models returns empty
Symptom: Clicking Sync models returns no models.
Cause: The API Address is unreachable, the network is restricted, or the endpoint does not support auto-fetching the model list.
- Confirm the API Address starts with https://api.aicodewith.ai/v1
- Switch network and retry
- Click + and type a Model ID to use the provider manually
Need the full guide?
Every config parameter, the complete model list, and more troubleshooting live in the AI Code With docs.
Open the AI Code With docs