The best models for Roo Code
— free to start
Connect Roo Code to Kyma's active open models. Auto-failback, prompt caching, OpenAI-compatible.
Multi-Mode Ready
Different models for Architect, Code, Edit, and Debug modes. Kyma lets you switch models per mode without switching providers.
Auto-Failback
If one provider is slow, Kyma routes to the next. Your coding flow never stops.
Prompt Caching
Repeated context? Kyma caches it. Save up to 90% on input tokens for iterative coding sessions.
Recommended Models for Roo Code
Picked for quality, speed, and tool use — matched to Roo Code's multi-mode workflow.
Top quality, 131K context. Perfect for Roo Code's Architect and Code modes.
qwen-3.6-plus#1 on Kyma
262K context, multimodal, strongest tool use. Ideal for autonomous coding.
kimi-k2.5Best Agentic
Highest SWE-bench globally. Use for complex refactoring.
minimax-m2.580.2% SWE-bench
Lightning fast on Groq. Best for Roo Code's quick edit mode.
qwen-3-32bUltra Fast
GPT-4 class quality at fraction of the cost. Great all-rounder.
deepseek-v3Near Frontier
Setup in 30 Seconds
1. Get your free API key → 2. Install Roo Code from the VS Code Marketplace → 3. Paste the config below.
1. Open VS Code → Extensions → Search "Roo Code" → Install 2. Click Roo Code icon → Settings 3. Set these values: API Provider: OpenAI Compatible Base URL: https://kymaapi.com/v1 API Key: ky-xxxxx (get yours at kymaapi.com) Model ID: qwen-3.6-plus Done! Roo Code now uses Kyma's models.
Roo Code supports multiple modes. Recommended models per mode: Architect Mode: qwen-3.6-plus (best reasoning) Code Mode: kimi-k2.5 (best tool use) Edit Mode: qwen-3-32b (fastest) Debug Mode: deepseek-v3 (deep analysis) Tip: Use model aliases for easy switching: "best" → qwen-3.6-plus "code" → qwen-3-coder "agent" → kimi-k2.5 "fast" → qwen-3-32b
Start coding with the best models — free
$0.50 free credits on signup. No credit card required.
Get Free API Key