Docs

Cherry Studio

Cherry Studio's custom provider takes a separate root address per protocol — OpenAI, Anthropic, Gemini. Paste the key and the roots, press Sync Models, and the catalog fills the picker by itself.

Settings → Model Services → a custom provider: paste the key and the API address, click Get Model List, and the whole catalog fills the picker.

Cherry Studio

设置 → 模型服务 → 添加 → 添加自定义提供商 (Settings → Model Services → Add → Add Custom Provider)

  提供商名称 / Provider name    Kunavo
  API 密钥 / API Key            sk-kn-...
  端点设置 / Endpoint settings
    OpenAI                     https://api.kunavo.com/v1
    Anthropic                  https://api.kunavo.com
  → 同步模型 (Sync Models), then add the models you want
  → 检测 (Test) to confirm

同步模型 / Sync Models calls GET /v1/models against whichever field's root you filled in, with the key you entered, so it is also the fastest test of whether that pair is right — an empty list almost always means the key or the address, not the provider.

Each endpoint field takes a root address, not a full endpoint URL. Cherry Studio appends its own version segment (skipped if your root already ends in one, so https://api.kunavo.com and https://api.kunavo.com/v1 both resolve correctly for the OpenAI field) and then always appends its own route for that field. Paste the full endpoint URL — one already ending in /chat/completions or /messages — and that route gets appended a second time, and the request 404s.

No key yet? Create a Kunavo account, make a key (it starts with sk-kn-) and add credit from $10 — calls are paid from that balance, and failed calls are not billed. The dashboard then opens on the Cherry Studio setup.

Step by step

Create a key at /app/keys and copy it — it is shown once.
Open 设置 → 模型服务 (Settings → Model Services) and 添加自定义提供商 (Add Custom Provider).
Fill in API 密钥 (the key) and the OpenAI endpoint field (https://api.kunavo.com/v1).
Fill the Anthropic field too (https://api.kunavo.com) — it sits under OpenAI in 端点设置 (Endpoint settings). Cherry Agent and any model routed over the Anthropic Messages protocol read from this field specifically, not the OpenAI one. The other endpoint types are under 更多设置 (More options).
Save, then press 同步模型 in the provider's model list and add the chat models you want; 检测 to verify one of them end to end.
Assign models per assistant rather than globally — Cherry Studio keeps a model per assistant, which is what makes a cheap default and an expensive specialist coexist.

Checked against Cherry Studio's provider documentation on October 1, 2026. Third-party settings move; if a field name here no longer matches what you see, that page is the authority, not this one.

Verify before you debug the client

One request settles whether a failure is the endpoint, the key, or the configuration file. If this returns JSON, the same base URL and key work in Cherry Studio.

# Settles whether a failure is the endpoint, the key, or the client.
curl -sS https://api.kunavo.com/v1/models \
  -H "Authorization: Bearer sk-kn-..."

Which model id to put in the field

Every text model is reachable as a model id — the live list is GET /v1/models, and the catalog with prices is on the models page. Rates are USD per 1M tokens, input / output.

Model id	Kunavo in / out	Where it fits in Cherry Studio
`claude-sonnet-5`	$1.40 / $7.00	the everyday assistant
`claude-opus-5`	$3.50 / $17.50	an assistant kept for hard problems
`claude-haiku-4-5`	$0.70 / $3.50	translation, summarising, anything high-volume
`gpt-5-6-terra`	$0.70 / $4.20	long documents and large pasted context

Billing is per token from a prepaid balance with no monthly fee — see billing. On repeated context — which is most of what an editor or a chat client sends — prompt caching moves the bill more than the model choice does.

Frequently asked questions

How do I add a custom API provider to Cherry Studio?

Open Settings → Model Services (设置 → 模型服务) and Add Custom Provider (添加自定义提供商). It takes a separate root address per endpoint type — OpenAI and Anthropic shown by default, with OpenAI Responses, Gemini and the image endpoints under More options (更多设置) — plus one API key. Enter the key and whichever endpoint roots you need, press Sync Models (同步模型) to pull the catalog, add the models you want, and use Test (检测) to confirm one works.

Why does Cherry Studio's Sync Models return nothing?

That button calls the OpenAI field's /v1/models route with the key you entered, so an empty result points at that field's address or the key rather than at Cherry Studio. Each field takes a root address — Cherry Studio appends the version and route itself — so check you haven't pasted a full endpoint URL (one already ending in /chat/completions), then try the same pair with curl: JSON back means the problem is in the app, a 401 means the key.

What does a # at the end of Cherry Studio's endpoint field do?

Cherry Studio's own docs describe it as pinning the field to a fixed path, for endpoints whose route doesn't follow the standard shape. Kunavo's OpenAI and Anthropic endpoints are both standard, so you don't need it — enter the root address, with or without your own /v1, and let Cherry Studio append the rest.

Can Cherry Studio use Claude models without an Anthropic account?

Yes, when a gateway serves them — put Kunavo's address in the Anthropic field specifically, not the OpenAI one, since Cherry Agent and any model routed over the Anthropic Messages protocol read from that field. Cherry Studio sends the model id to whatever endpoint the provider entry names, so a Claude id resolves there and the only credential Cherry Studio holds is the endpoint's key.