How to connect Cherry Studio to the Tokenator API

Cherry Studio is a desktop chat client that can talk to any OpenAI-compatible server. Setup fits in a single dialog, but the client completes the address on its own, so the trailing slash decides whether the connection works at all.

Get an API key API documentation

What you end up with

Once configured, Cherry Studio stops talking to its default provider and sends every request to Tokenator. Billing comes out of your key's token limit, and the list of available models is defined by the key rather than by the tool.

Tool	Cherry Studio
Protocol	OpenAI-compatible
Base URL	`https://api.tokenator.top/v1/`
Key	`sk-your-tokenator-key`

Requirements and supported operating systems

Windows 10/11, macOS 12+, or a modern 64-bit Linux.
Outbound HTTPS access to the Tokenator domain.
A Tokenator API key that looks like sk-your-tokenator-key.

You need the Cherry Studio desktop build. No Node.js, no editor and no account in the client itself — everything is configured in the UI.

Installing Cherry Studio

Download the build for your system from the project's official site and install it the usual way. Cherry Studio needs no sign-up: the client keeps its settings locally and runs on your key.

Setting up Tokenator

Register in your account and buy a token bundle.
The key appears in the account right after the payment is confirmed — copy it whole, including the prefix.
The examples below use the placeholder sk-your-tokenator-key. Never publish a real key in repositories or screenshots.

Configuration

Open Settings (the gear icon in the bottom left corner) and go to Model Providers.
Scroll the provider list down and press + Add.
Provider type: OpenAI. The name is up to you, for example Tokenator.
API key: sk-your-tokenator-key
API address: https://api.tokenator.top/v1/ — with the trailing slash.
In the Models block press + Add and paste a model ID, for example gpt-5.5. Repeat for every model you need.
Enable the provider toggle in the list on the left and save.

The trailing slash is mandatory. Cherry Studio completes the address on its own: if it does not end with /, the client appends /v1. The Tokenator address already contains /v1, so without the slash the request goes to /v1/v1/chat/completions and comes back as an error. For the same reason the address must not be shortened to https://api.tokenator.top in the hope that the client will add the version — only the full address with the slash works.

Cherry Studio keeps these settings in its application profile rather than in environment variables, so the steps are identical on Windows, macOS and Linux. The client does not fetch the model list from the provider: models you did not add by hand will not show up in the chat picker.

Your first request

Before starting the tool it helps to confirm that the key and the model both work. A single curl request answers both questions.

OpenAI endpoint check

curl https://api.tokenator.top/v1/chat/completions \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "ping"}]
  }'

Next to the key field in the provider card there is a Check button that sends a probe request with the selected model. A successful check means the key and the address are correct. After that open a new chat and pick the model in the selector at the top.

A successful response means the key is valid, the model is allowed for it and the upstream is reachable. Usage appears in your account right after the request.

Switching models

Models are added by hand in the provider card, under Models: the client does not ask the server for the list. Paste the ID exactly as it appears in the catalog, with no prefixes. The base URL and the key stay the same when you add another model.

Examples of model IDs available right now:

claude-haiku-4-5
claude-opus-4-6
claude-opus-4-7
claude-sonnet-4-6
gpt-5.5
deepseek-v4-flash

Current IDs and specs live in the AI model catalog, which also shows which models are available right now. The model comparison helps choose between close options.

Configuring reasoning

If the tool can send a reasoning_effort field, Tokenator forwards it upstream unchanged. On top of that the key itself has a reasoning switch in your account, which works independently of the tool.

Common errors and how to fix them

Symptom	Cause	Fix
404 or "not found" on every request	The API address has no trailing slash, so the client appended a second `/v1`.	Open the provider card and make sure the address ends with `/v1/`.
The model you need is missing from the chat	The model was not added by hand under "Models" — the client does not pull the list from the server.	Add the exact model ID from the catalog and enable the provider toggle.
`401` or an invalid-key message	The key was copied with stray spaces, was revoked, has expired, or landed in the wrong environment variable.	Check the key in your account and make sure the environment variable actually reached the process running the tool.
`403`	The model is not in the key's allowed-model list.	Check the key's model list in your account and pick an ID from the model catalog.
`429`	The per-minute or per-hour request limit, or the concurrent-stream limit for the key, was exceeded.	Lower the agent's concurrency and retry with exponential backoff. Key limits are visible in your account.
Model not found / not supported	The request used an ID that is not in the catalog, or an alias unavailable to this key.	Copy the exact API ID from the model page — case and dots matter.
The request hangs or breaks on a long answer	The client closed the connection on its own timeout before the model finished generating.	Turn on streaming (`stream: true`) and raise the client timeout: with long reasoning answers the first token can take a while.
A bare "Request error" with no details	The upstream provider returned an error. Its text is not passed through to the client.	Retry: Tokenator fails over to the next provider for the model on its own. If it persists, contact support.

FAQ

Do I need a Cherry Studio subscription or a separate provider account?

No. The tool talks to Tokenator, and billing comes from your Tokenator key's tokens.

Where do I see usage after connecting?

In your account: it shows requests, spent tokens and the key's remaining limit.

Can one key be used in several tools?

Yes. The limits are the key's own: requests per minute and hour, plus the number of concurrent streams.

What happens if tokens run out mid-session?

Requests start returning an error. Topping up the same key restores the limit — no need to reinstall the tool.

How do I switch back to the previous provider?

Remove the settings you added — the environment variables or the provider block in the config. The tool reverts to its default behaviour.

Where can I read about the API format itself?

In the Tokenator API documentation and on the OpenAI-compatible API page.