Integration
Cherry Studio with LLMcode
Cherry Studio is a desktop client for multiple providers. Add LLMcode as an OpenAI-compatible provider and pick models from the catalog.
Updated
Add the provider
In provider settings, add a custom OpenAI-compatible provider. Base URL: https://llmcode.io/v1. Paste the key and add the published model slugs.
Fetching the model list should return the published profiles; if it does not, the key or network is the problem.
Desktop keys
Treat the desktop key as less trusted: set a spend limit and expiry, and revoke it if the machine is lost.
For team use, issue one key per person so usage stays attributable.
Images and audio
LLMcode serves chat, responses and embeddings. Image, audio and video endpoints are not part of this version, so desktop features that rely on them will not work.
Connect
Provider type: OpenAI Compatible
Base URL: https://llmcode.io/v1
API key: sk-llmcode-…
Models: flash, standardPublished model prices
USD per 1M tokens. The numbers come from the public catalog on every page rebuild — this is the sale price, not an estimate.
| Model | Input | Output | Cache |
|---|---|---|---|
| Claude Opus 5.5 | $2.70 | $8.00 | $0.14 |
| DeepSeek Flash | $0.50 | $2.00 | $0.01 |
| Claude Sonnet 5.5 | $1.33 | $6.67 | $0.07 |
| DeepSeek V4 Pro | $2.20 | $6.60 | $0.07 |
Top-up from $10, balance in USD. 1 USD = 1,000,000 UT. No subscription and no auto-charge.
Questions
Which provider type do I choose?
OpenAI-compatible (custom OpenAI provider), with base URL https://llmcode.io/v1.
Can I use several keys?
Yes. One key per device or person makes usage and revocation cleaner.
Are image models supported?
No. This version serves text and embeddings only.