# Cherry Studio

> Add an OpenAI-type model service in Cherry Studio that points at Relayvia.

Cherry Studio connects through an OpenAI-type model service and shows your credits through the OpenAI legacy endpoint described in [Check credits](https://relayvia.dev/docs/api/balance).

## Install

Download Cherry Studio from the [official site](https://www.cherry-ai.com/download).

## Settings screen

Settings → Model Services → Add, choose type OpenAI, enter the API address and API key, then add models under Manage. Do not add /v1 to the API address; Cherry Studio appends it.

| Field | Value |
| --- | --- |
| Type | `OpenAI` |
| API address | `https://api.relayvia.dev` |
| API key | `sk-...` |
| Model ID | `gpt-5.5` |

Replace `sk-...` with an API key from the console.

## Environment variables

> **Note**
>
> This tool does not read environment variables; use the settings screen above.

## Troubleshooting

| Symptom | Cause | Fix |
| --- | --- | --- |
| 401 invalid_api_key | Wrong, disabled or expired API key | Check the key's status in the console and copy the full string starting with `sk-`; create a new key if needed. |
| 402 insufficient_quota | The account's credits, the key's limit or the team member's limit is used up, or the account is frozen | Top up, or ask an admin to raise the limit. Retrying will not help. |
| 403 forbidden | The key may not use the model, the source IP is not on the allowlist, or the account is disabled | Check the key's allowed models and IP allowlist; use official model names as listed by `/v1/models`. |
| 429 rate_limited | Too many requests | Wait for `Retry-After` and retry; contact us if you regularly need more. |
| Cannot connect (timeout, DNS error or 404) | Wrong base URL or no network access | Make sure the API address is `https://api.relayvia.dev`, with no trailing /v1 or slash. |