Skip to main content
Aider is an AI pair programming tool that works in your terminal. It supports OpenAI-compatible APIs natively.

​
Configuration

Then run:
Or for a specific model:
Every model in this table runs on the signup credit, which is added once your email is verified and spends on the free tier. Models outside the free tier return 402 model_requires_paid until your first top-up.
See all model aliases for shortcuts.

​
Notes

  • Aider uses the openai/ prefix for model names: openai/best or openai/qwen-3.6-plus.
  • Model aliases work with Aider: --model openai/code.
  • For large codebases, use deepseek-v4-flash (1M context, free tier), or long-context (gemini-3-flash, 1M context) after your first top-up.
  • Kyma falls back across routes when one fails; if every route for a model is down, the request returns 503.

​
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.