Skip to main content
Kilo Code is an open-source AI coding agent for VS Code and the terminal. Venice is available as a native provider, so you can select Venice models without configuring an OpenAI-compatible custom endpoint.

Native Provider

Built-in Venice support in Kilo’s Providers settings

VS Code + CLI

Same kilo.json config works across the extension and CLI

Reasoning Models

Kilo maps Venice reasoning controls when the model supports them

​
Prerequisites

​
Setup

1

Install Kilo Code

In VS Code, open Extensions, search for Kilo Code, and install it from the Visual Studio Marketplace.Prefer the Marketplace Pre-Release channel when that is the current recommended build — see Kilo’s install docs.
2

Get your Venice API key

Generate a key from venice.ai/settings/api. Copy it immediately and store it securely.
3

Add the Venice provider

Open Kilo Settings (gear icon) and go to the Providers tab. Select Venice AI and paste your Venice API key.The extension stores the provider in your kilo.json config. You can also edit that file directly — see the CLI tab for the format.
4

Select a model and test

Choose a Venice model from the model picker, then send a small task such as:
Browse available IDs in the text model catalog.

​
Verify the Venice API

If Kilo cannot connect, confirm the key and model IDs independently:
Copy a model’s id exactly into Kilo. In CLI config, prefix it with venice/, for example venice/zai-org-glm-5-1.

​
Configuration Notes

  • Venice is a native Kilo provider. Prefer Venice AI in Providers settings over a generic OpenAI-compatible custom endpoint.
  • The extension and CLI share the same config files (~/.config/kilo/kilo.json globally, or ./kilo.json in a project).
  • Some Venice models expose reasoning controls. Kilo maps supported reasoning effort and disable-thinking options when the selected model supports them.
  • Model IDs and plan access can change. Use the model picker, text model catalog, or GET /models for the current list.
  • Keep your Venice API key private. Do not paste it into source files or commit it to git.

​
Troubleshooting

Confirm the key comes from venice.ai/settings/api. For the CLI, verify VENICE_API_KEY is set in the same environment that launches Kilo. In VS Code, reconnect Venice AI under Providers.
Confirm your Venice account has access to the selected model, copy the ID from the text model catalog or GET /models, and for CLI config use the venice/<model-id> form.
Update to the current recommended Kilo build (including Pre-Release when that is the documented default). You can also set the provider in kilo.json as shown in the CLI tab — the extension reads the same config.

​
Resources

Kilo Venice Provider Docs

Official Kilo Code Venice setup

Venice Text Models

Browse available Venice model IDs

Kilo Install Docs

VS Code, CLI, and other platforms

Venice API Reference

Full endpoint and parameter docs