Windsurf - Kyma API

Windsurf supports OpenAI-compatible providers for custom models.

Setup

Open Windsurf → Settings → AI Provider
Select “OpenAI Compatible”
Fill in:

Field	Value
Base URL	`https://kymaapi.com/v1`
API Key	Your `ky-` key
Model	`llama-3.3-70b`

Recommended Models

Model	Alias	Best For
`qwen-3.6-plus`	`best`	Recommended — highest quality
`qwen-3-coder`	`code`	Best alias for code-focused tasks
`kimi-k2.6`	`agent`	Best tool calling
`llama-3.3-70b`	`balanced`	Great all-rounder
`deepseek-v4-pro`	—	1M context, top reasoning. Complex refactors and long-codebase tasks.
`deepseek-v4-flash`	—	1M context, value tier. Everyday completions where speed matters.

See all model aliases for shortcuts.

Prompt Caching

Prompt caching is automatic. Your system prompt and tool definitions are cached for 5 minutes, and the repeated part then bills at that model’s cached-input rate instead of its input rate. No code changes needed. See Prompt Caching for details.