Set up Cherry Studio with InferSpeed: API address and key
In Cherry Studio, add an OpenAI-compatible provider with InferSpeed's API address and your key, then add the model glm-5.3. You pay per token.
The provider type, key and model match the OpenAI-compatible tools config in developers.md (2026-10-19). The API address is written the way Cherry Studio takes it, without /v1; see the FAQ below.
Add the provider
1. Create a key at https://inferspeed.ai/keys.
2. In Cherry Studio, open Settings → Model Services → Add (names may differ in your version) and fill in:
| Field | Value |
|---|---|
| Provider type | OpenAI |
| API key | Your InferSpeed key |
| API address | https://api.inferspeed.ai |
| Model | Add glm-5.3 |
3. Click "Check", pick glm-5.3, and once it passes, choose that model in a chat.
FAQ
The check returns 404?
Change the API address to https://api.inferspeed.ai/v1 and try again.
Can I use Kimi?
One key calls every live model (GET /v1/models lists the models your key can call); use the model ID kimi-k3. This page only gives the config for glm-5.3.
What are the default limits?
30 requests per minute and 5 concurrent requests for new accounts, across all keys of the account.
Prices (USD per 1M tokens)
| Model | Input | Output | Cache read | Official price (input / output) |
|---|---|---|---|---|
| glm-5.3 | $0.84 | $2.64 | $0.156 | $1.40 / $4.40 |
All models and live prices: https://inferspeed.ai/model-plaza