Kilo Code

From the settings#

In VS Code: Settings (gear icon) → Providers → at the bottom, Custom provider.

The list read from /v1/models also holds models that do not chat, such as bge-m3 and whisper-1. Leave those out.

From kilo.jsonc#

The context window, the output limit and the tool flag of each model are set in kilo.jsonc. This is the form Kilo Code's documentation gives for an OpenAI-compatible provider, with ITS INCOM AI's values:

{
  "$schema": "https://app.kilo.ai/config.json",
  "model": "openai-compatible/qwen3.8-27b",
  "provider": {
    "openai-compatible": {
      "options": {
        "apiKey": "{env:API_KEY}",
        "baseURL": "https://api.ai.itsincom.org/v1"
      },
      "models": {
        "qwen3.8-27b": {
          "name": "Qwen3.8 27B",
          "tool_call": true,
          "limit": { "context": 131072, "output": 32768 }
        }
      }
    }
  }
}

{env:API_KEY} reads the key from the environment variable API_KEY. Keep the key in the global file, in ~/.config/kilo: a kilo.json committed to a project cannot read environment variables.

For another model, add an entry under models with its id and the context window from Which model.

Which model#

qwen3.8-27b for most work, for its 131,072 tokens of context. qwen3-coder-30b for quick tasks. More in Which model.

Limits#

• output up to 32768. The API refuses a max_tokens above 32,768 with 422.
• No reasoning to show: the API does not return a model's reasoning.