Set up Obsidian Copilot
Chat with, rewrite and summarize your Obsidian notes using CherryChat models
- API format: OpenAI Chat Completions
- Base URL format: Up to /v1 (https://gpt.cherrychat.org/v1)
- Recommended model: gpt-6.1-sol, claude-sonnet-5-5
- Platforms: macOS, Windows, Linux, iOS, Android
Steps
Install the Copilot plugin
In Obsidian, open Settings → Community plugins → Browse, search for Copilot, install it and enable it.
Add a custom provider
Open Settings → Copilot → the BYOK tab → "Add a provider" → "Add a custom provider".
Fill in the provider details
Set Display name to CherryChat. Type a model in "Model ID" and click Add (repeat for more). Leave "Enable CORS" off for now.
- API key: sk-your-key
- Base URL: https://gpt.cherrychat.org/v1 (Must include /v1)
- Model ID: gpt-6.1-sol
Test and save
Click Test, then Save. If Test passes but chat messages fail, edit the provider and turn on "Enable CORS" (replies then arrive all at once instead of streaming).
Set the default model and start
Go to Basic → Agents → Quick Chat and set "Default model" to the CherryChat model. Open the Copilot chat panel and send a message.
Common pitfalls
- Base URL must include /v1 (https://gpt.cherrychat.org/v1); the plugin also lists models from https://gpt.cherrychat.org/v1/models.
- This is the Copilot 4.x UI. On 3.x use the Model tab → "Add Custom Model" with Provider "3rd party (openai-format)"; the Base URL, key and model are the same.
- In 4.x semantic search (formerly Vault QA) is provided by Miyo, so no embedding model is needed in Copilot. Only 3.x Vault QA needs an extra embedding model, text-embedding-3-small, with the same Base URL and key.
- The key is stored in this device's Obsidian Keychain and does not sync with the vault; enter it again on other devices.
- Claude and Codex in Agent Chat use their own CLI logins, not BYOK; see the Claude Code and Codex guides to point them at CherryChat.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| Invalid key / 401 | The key is wrong, has spaces, or was disabled | Copy the key again from My Keys, paste it and click Test |
| Check failed or 404 | Base URL is missing /v1 or was set to https://gpt.cherrychat.org/v1/chat/completions | Change it to https://gpt.cherrychat.org/v1 and test again |
| Test passes but chat fails | A compatibility issue with how Quick Chat sends requests | Edit the provider, turn on "Enable CORS" and save |
| Model not found | Model ID is misspelled (case or spaces) | Copy it from the Models page, e.g. gpt-6.1-sol |
| HTTP 402 or "insufficient balance" (billing_error in Claude format) | Your credits cannot cover this call. API calls are paid from credits only; memberships and unlimited plans do not apply | Top up any amount in the CherryChat Store, then retry after a few seconds |
| HTTP 429 Too Many Requests | Too many requests: by default 120 per minute per key and 8 at a time per account | Lower the concurrency or requests per second in the tool and wait for the Retry-After seconds; most tools retry on their own |
Guide checked 2026-11-02. The tool's screens may change; the official docs win if they differ.
Operated by UK Company CHERRYCHAT LTD · Company Number 16096119 · Support WeChat: JsnonoChat · Content is AI-generated — please verify before relying on it
