Cherry Studio

Steps

• Create a custom Provider and choose OpenAI Compatible or OpenAI.
• Use https://www.zltokens.com/v1 when the client asks for OpenAI Base URL; use https://www.zltokens.com if it appends /v1/chat/completions automatically.
• Load models from the list or manually add public platform model names.
• Image input requires both model capability and configured image pricing.

Verification

• Send a short text with images, files, and long context disabled.
• When checking pricing, Tidal Tokens, or channel issues, start from request_id, model, tokens, channel, and error body.

Verification and troubleshooting

• Use OpenAI Compatible or a custom Provider; avoid a doubled /v1/v1. If model discovery fails, enter the public platform model name manually.
• The first request should appear as /v1/chat/completions in usage logs. If no record appears, stop and check the URL, Key, and protocol.

Official version reference

• Client configuration can change by version. Before deployment, troubleshooting, or a configuration change, check [Cherry Studio Provider settings](https://docs.cherry-ai.com/cherry-studio-wen-dang/en-us/cherry-studio/preview/settings/providers).