Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.kodus.io/llms.txt

Use this file to discover all available pages before exploring further.

Yes. Kodus supports Bring Your Own Key (BYOK) on every plan, letting you use your preferred LLM provider. You pay the provider directly — Kodus never marks up tokens and never sees your key in plain text.

​
How it works

  1. Open Settings → BYOK (app.kodus.io/organization/byok)
  2. Pick a recommended model from the curated catalog, or click Configure manually for any other provider/endpoint
  3. Paste your API key and click Test & save — Kodus validates the key with a cheap metadata call before persisting
Ready-to-click cards with pre-tuned defaults (temperature, max tokens, reasoning level):
  • Claude Sonnet 4.6 / Opus 4.7 (Anthropic)
  • Gemini 3.1 Pro custom tools (Google)
  • GPT-5.4 (OpenAI)
  • Kimi K2.6 Coding (Moonshot AI — Developer API or Kimi Code Plan)
  • GLM 5.1 (Z.ai — Developer API or Coding Plan)
For models outside this list, the Configure manually wizard walks you through any OpenAI, Anthropic, Google, OpenRouter, Novita, or OpenAI-compatible endpoint.

​
Why use your own provider

  • Data control — requests go directly to your provider
  • Cost management — use your existing billing relationship, no markup
  • Model choice — pick the model that works best for your codebase
  • Compliance — meet internal requirements for AI tool usage
  • Fallback resilience — configure a Main + Fallback to keep reviews running during provider outages

​
Self-hosted LLM providers

If you self-host Kodus, you can point BYOK at self-hosted or aggregator endpoints like:
  • Novita, Groq, Together AI, Fireworks AI
  • Chutes, Synthetic
  • Your own Ollama / vLLM / TGI instance (via the OpenAI Compatible provider)
For setup guides, see the Cookbook and the provider-specific docs in the knowledge base. For the full BYOK flow (catalog, manual wizard, plan selectors, advanced tuning), see Bring Your Own Key.