What does Loomy do? Do I need a plugin?

Loomy is iFlytek's desktop AI client for managing models and chats locally. This page uses a custom provider — no extra plugin is required.

Why does the Base URL include /v1?

Loomy treats the value as the OpenAI-compatible root and appends the API path itself. Set the URL to https://api.aicodewith.ai/v1. Adding /chat/completions by hand causes a 404.

Why can't I use the built-in Zhipu card?

The built-in Zhipu card has no Base URL field, so you cannot point it at AI Code With. Click Add provider and use a custom provider.

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, then paste it into Loomy's API Key field.

How do I confirm the setup works?

After Fetch from API succeeds, click Save and apply, then return to chat, pick the model you just added, and send a test message. A normal reply confirms the connection; match the call by time and model in usage records.

Loomy × AI Code With

Use AI Code With in Loomy: Third-Party API / Relay Setup

This page shows how to connect a third-party API in Loomy's desktop client so you can manage models and chats locally with a custom provider.

Download and install Loomy first, then add a custom provider in Settings. Enter the key only in the app, never on this page.

I have Loomy: set it up Install Loomy

Custom provider quick reference4 settings

Provider ID: aicodewith
Display name: aicodewith
npm package / SDK mode: OpenAI Compatible
Base URL: https://api.aicodewith.ai/v1

Quick setup

In Loomy Settings, add a custom provider: fill identity and Base URL first, then paste the key and fetch models from the API. About 3 minutes.

Loomy is a desktop client. Open Settings, go to Models → Provider config, then click Add provider. Fill identity and Base URL in Add custom provider, then paste the key and fetch models on the next screen.

Fill the provider identity
Open Loomy Settings, go to Models → Provider config, then click Add provider. Set Provider ID and Display name to aicodewith, SDK mode to OpenAI Compatible, Base URL to https://api.aicodewith.ai/v1 (include /v1), then click Next. Do not use the built-in Zhipu card.
Quick copy
Provider ID
aicodewith
Display name
aicodewith
npm package / SDK mode
OpenAI Compatible
Base URL
https://api.aicodewith.ai/v1
Click Add provider to open Add custom provider. Set Provider ID and Display name to aicodewith, SDK mode to OpenAI Compatible, Base URL through /v1, then click Next.
2
Paste the key and fetch models
On Configure aicodewith, paste the API key and click Fetch from API. If a model is missing, click Add model and paste a Model ID from this page. When the list looks right, click Save and apply.
Quick copy
Open the API key page
Copy a Model ID
The next screen fetches the model list after Fetch from API. Copy a Model ID below, then search the list; if it is missing, click Add model and paste it.
Pick a family, then copy a Model ID. The Base URL stays the same for every model.
Selected
Provider
Claude
Model ID
claude-sonnet-4-6
The full catalog follows the AI Code With docs and pricing page. Example IDs in screenshots only show where to enable a model; use an ID from this page.
View the full model list
Paste the API key, then click Fetch from API. If a model is missing, click Add model and paste a Model ID from this page. When the list looks right, click Save and apply.
Send a test message
Return to chat, pick the model you just added, and send a test message. A normal reply confirms the connection — then match the call by time and model in AI Code With usage records.
Return to chat, pick the model you just added, and send a test message. A normal reply confirms the connection. Match the call by time and model in AI Code With usage records.

How does Loomy connect to AI Code With?

Loomy talks to an OpenAI-compatible API through a custom provider. Connecting to AI Code With means filling the provider identity, pasting the key, then fetching models:

Open Add custom provider: Open Loomy Settings, go to Models → Provider config, then click Add provider. The Add custom provider dialog opens. Do not use the built-in Zhipu card — it has no Base URL field.
Fill identity and URL: Set Provider ID and Display name to aicodewith. Set npm package / SDK mode to OpenAI Compatible. Set the Base URL to https://api.aicodewith.ai/v1 (include /v1, do not append /chat/completions). Then click Next.
Paste the key and fetch models: On the Configure aicodewith page, paste the API key and click Fetch from API. If a model is missing, click Add model and paste a Model ID from this page.
Save and apply: When the list looks right, click Save and apply. Saving is not success — send a test message in chat next.
Send a test message: Return to chat, pick the model you just added, and send a test message. A normal reply confirms the connection.

Flow: Loomy app → custom provider (Base URL + key) → AI Code With API. Everything is configured in Settings. No files to edit.

Frequently asked questions

New to Loomy?

Loomy is iFlytek's desktop AI client for macOS 14+ Apple Silicon and Windows 10+ x64.

Loomy website

Download the installer for your OS from the official site. After install, open Loomy and go to Models → Provider config in Settings.

Open the Loomy download page

Full install guidance follows the Loomy official site; this site does not host the installer. If the site asks for an invite code, the public code is 7DVZNJ. The invite code is not a setup-success condition.

Common error troubleshooting

The most frequent problems fall into 4 categories.

401 / Invalid API key

Symptom: Fetch from API, or a chat message, returns 401, Unauthorized, or Invalid API Key.

Cause: Usually the API key is invalid, mistyped, or copied with extra characters.

Go back to Configure aicodewith and re-paste the API key (no extra spaces)
Confirm the key is a valid AI Code With API key
Click Fetch from API again

404 / Wrong Base URL

Symptom: Fetching models fails, or the request hits .../v1/chat/completions/chat/completions.

Cause: The Base URL was set to the full chat completions path. Loomy appends the path itself, so the URL should stop at /v1.

Set the Base URL to https://api.aicodewith.ai/v1 only — do not add /chat/completions
Use Add provider, not the built-in Zhipu card
Do not leave a trailing slash

Model not enabled / model not found

Symptom: The chat window cannot select the model you just added, or sending a message says the model does not exist.

Cause: You did not pick the model in chat after saving, or the Model ID is not in the list.

Click Save and apply
If it is missing, click Add model and paste a Model ID from this page
Confirm the key can access that model

Connection fails / no chat reply

Symptom: Fetch from API fails, or sending never returns a reply.

Cause: The network is restricted, the provider is unsaved, or the model is unavailable for this key.

Confirm the custom provider is saved and enabled
Try another model listed on this page
Check AI Code With usage records for a matching call

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