Skip to main content

​
Setup

1

Open Cursor Settings

Cmd+, (Mac) or Ctrl+, (Windows) → search “OpenAI”
2

Configure API

Set the following:
  • OpenAI API Key: kyma-your-api-key
  • API Base URL: https://kymaapi.com/v1
3

Select model

Add custom model: qwen-3.6-plus or qwen-3-coder (both run on the free tier)
4

Start coding

Use Cmd+K to chat with AI using Kyma’s models.
A new account’s signup credit is added once your email is verified and spends on free tier models only. Models outside it return 402 model_requires_paid until your first top-up; for 1M context on the free tier, use deepseek-v4-flash.
Use model aliases like best or code. We repoint an alias by hand when a better model ships; pin a full model id if you need a model that never changes.

​
Audio Models (optional)

Cursor is a coding IDE first, but if you bolt audio tooling onto your workflow (voice notes, meeting recap macros, audio QA fixtures), Kyma’s audio aliases work the same as any chat model:
  • transcribe → whisper-v3-turbo — 228× realtime speech-to-text
Use them via POST /v1/audio/transcriptions. Text-to-speech is documented in the Audio API reference and Model Aliases.

​
Prompt Caching

Some models cache a repeated prompt prefix. pricing.cached on /v1/models is the rate Kyma publishes for cached input on that model — usually below its input rate, but not always, so compare the two for the model you use. Every chat completion reports usage.cost, what the request was charged, and usage.cache_discount, Kyma’s figure for what caching saved on it. Whether a prefix is cached automatically or needs a cache_control marker depends on the model’s creator. See Prompt Caching for details.