Bring your own models
to Cursor
Use Kyma's active open models in Cursor. Supported features depend on your Cursor plan and version; compare model options and usage-based pricing.
Better Model Selection
Access active models including Kimi K2.6, DeepSeek V3, Qwen 3.6 Plus: models not available in Cursor's default lineup.
Pay per use
Kyma API bills model usage separately from your Cursor plan. Compare rates on the pricing page.
Automatic fallback
For eligible failures, Kyma API tries another compatible route when available. Your app should still handle errors.
Recommended Models for Cursor
Chosen for Cursor's chat, composer, inline edit, and agent modes.
Supports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.
qwen-3.6-plusSupports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.
kimi-k2.6Supports tool use. Compare current prices and measured uptime on the model page.
qwen-3-coderSupports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.
gemini-3-flashSupports reasoning, tool use, vision input. Compare current prices and measured uptime on the model page.
gemma-4-31bSetup guide
1. Create account → 2. Follow the steps below → 3. Pick your model.
1. Open Cursor → Settings (Cmd+,) 2. Search "OpenAI" in settings 3. Set these values: OpenAI API Key: kyma-xxxxx (your Kyma key) Override OpenAI Base URL: https://kymaapi.com/v1 4. In chat, type a model name: @qwen-3.6-plus or @kimi-k2.6 That's it! Cursor now uses Kyma's models.
Best models for each Cursor feature: Chat: qwen-3.6-plus (best reasoning) Composer: kimi-k2.6 (best multi-file) Inline Edit: qwen-3-coder (fast + accurate) Agent Mode: kimi-k2.6 (best tool calling) Pro tip: Use model aliases: "best" → qwen-3.6-plus "code" → qwen-3-coder "agent" → kimi-k2.6 "fast" → gemini-3.5-flash-lite
Connect Cursor to Kyma API
$0.50 signup credit for eligible free-tier models after email verification. No card required.
Create account