Kilo Code
Kilo Code is a coding agent for VS Code. It reaches Inferray through its OpenAI Compatible provider.
Set it up
- Install Kilo Code from the VS Code Marketplace and open its panel.
- Open Settings → Providers and add a provider.
- Choose OpenAI Compatible as the API provider.
- Set Base URL to
https://api.inferray.com/v1and API Key to your Inferray key. - Enter a Model ID from the catalogue, such as
claude-sonnet-4-6. - Save, and select the model in the chat's model picker.
Pick a model with tool support: Kilo Code's agent reads files, edits code and runs commands through tools. Set the context window in the model settings to the model's context length from its catalogue page, so long sessions are trimmed at the right point.
Check it worked
Ask Kilo to explain a function in the open file. A reply means the connection works; the request appears in your logs.
Tips
- Select the model in the chat itself. Changing the default in settings does not always change the active chat.
- Start in a review-first mode so you approve edits and commands before they run.
Models that work well here
- Claude Opus 5.5$4 in · $20 out per 1M tokens
- Claude Sonnet 5.5$2 in · $10 out per 1M tokens
- GPT-6.1 Sol$2 in · $10 out per 1M tokens
- Gemini 4 Argon$4 in · $20 out per 1M tokens
- Kimi K3$3 in · $15 out per 1M tokens
- GLM-5.3$0.77 in · $2.42 out per 1M tokens
- Gemini 3.8 Flash$0.75 in · $3.75 out per 1M tokens
- DeepSeek V4.1 Flash$0.15 in · $0.6 out per 1M tokens
- Run it on a Token Plan$20 a month buys $60 of usage across these models, with no 5-hour windows or weekly caps.