Connecting DeepChat

Difficulty 🧩 Medium　|　API format OpenAI compatible　|　base_url https://byesu.com/v1

Setup · fill these in

API addresshttps://byesu.com/v1

API keysk-xxxxxxxxCreate in console →

Modelgpt-5.5

API format OpenAI compatible · model names follow the console

DeepChat is an open-source, cross-platform, full-featured AI client (a desktop app for Windows / macOS / Linux). It supports both cloud and local models and comes with multiple conversations, agents, tool calling, and more. Point its "provider" at byesu — an AI API gateway with OpenAI-compatible and Anthropic-native endpoints — and one key gives your local client access to Claude, GPT-5.6, Grok and Gemini models such as gpt-5.5, claude-opus-4-8, and gemini-3.1-pro-high, billed pay-as-you-go with no subscription.

Before you start

First go to Console → Tokens and create an API token (it looks like sk-xxxx).

When creating it, be sure to pick the right group — the group determines which models you can call and which route is used. Not sure which one to pick? See Choosing a group.

Step 1: Download and install DeepChat

Go to the DeepChat website or its GitHub Releases page, download the installer for your system (Windows .exe / macOS .dmg / Linux .AppImage), then install and open it.

Step 2: Add byesu as a provider

Open DeepChat, click Settings (the gear icon) → Model Providers in the bottom-left corner, and add a new provider.

Pick the correct provider type

byesu uses the OpenAI-compatible interface here. When adding a provider, choose the "OpenAI" or "OpenAI-compatible" type. Do not choose the Anthropic / Claude official type, or the address and authentication format will not match.

Fill in the following fields:

Field	What to enter
Name	byesu (anything you like, just so it's easy to recognize)
API address / API Host	https://byesu.com/v1
API Key	The token you created in the console, looks like sk-xxxx

After saving, turn on the toggle for this provider.

About the API address

DeepChat usually appends paths like /chat/completions to the address automatically. If the connection fails with a 404 error, try entering only https://byesu.com/v1 (don't add /chat/completions yourself). If it still doesn't work, try https://byesu.com instead and let the client append /v1 automatically.

Step 3: Add and enable models

Under that provider, go to the model list, click "Add model" or "Fetch model list", then manually enter the names of the models you want to use and enable them. Common models:

Recommended for chat

gpt-5.5
claude-opus-4-8

More options

gemini-3.1-pro-high

The model names must exactly match the models actually available on byesu, and they must be within the range allowed by the group your token belongs to.

Step 4: Run it and verify

Go back to the main screen, select the provider and model you just added from the model picker at the top (for example claude-opus-4-8), start a new conversation, and send a quick "Hello".

If you get a normal reply, the setup was successful.

Stuck?

• 401 / Authentication failed: The API Key is wrong or has extra spaces. Re-copy the full sk-xxxx from the console. See Common errors #auth for details.
• 404 / Endpoint not found: You manually added an extra /chat/completions to the API address. Remove it so the path ends at /v1, or use https://byesu.com instead and let the client append the rest automatically.
• No available channel / Model does not exist: The model name is misspelled, or the group your current token belongs to doesn't include that model. Double-check the model name and choose a group. See Common errors #no-channel for details.
• Insufficient quota / Balance is 0: Your account or token quota is used up. Top up (USDT, Alipay or WeChat Pay) or adjust the token's quota. See Common errors #balance for details.

For more troubleshooting, see Common errors and Choosing a group.