Kimi Code Integration

Kimi Code CLI is an open-source, AI-powered coding agent developed by Moonshot AI designed to automate software development tasks directly within your terminal. It can read and edit code, execute shell commands, search files, and autonomously manage complex coding workflows.

Kimi Code features first-class support for the models.dev registry, a community-maintained model catalog. This allows Kimi Code to query and configure Halfbill dynamically — fetching the available models, capabilities (such as thinking or vision), and pricing without requiring manual TOML editing.

Prerequisites

• A Halfbill API key — sign up

Setup

Install Kimi Code CLI

If you haven't already, install Kimi Code CLI.

• macOS or Linux:

  curl -fsSL https://code.kimi.com/kimi-code/install.sh | bash

• Homebrew (macOS/Linux):

  brew install kimi-code

• Windows (PowerShell):

  irm https://code.kimi.com/kimi-code/install.ps1 | iex

Confirm the installation:

kimi --version

Launch Kimi Code and Open the Provider Manager

Start the interactive terminal in your project directory:

kimi

Once loaded, type the /provider command and press Enter. Select Known third-party provider to fetch the catalog from the registry:

Select Halfbill

Type llm to filter the providers and select Halfbill from the list:

Enter Your API Key

When prompted, paste your Halfbill API key and press Enter. Kimi Code will save it to your local configuration.

Your credentials are saved locally to ~/.kimi-code/config.toml.

Select a Model and Toggle Thinking

The Halfbill catalog is now loaded. Use the arrow keys to browse or type to search for your desired model. Select the llmgateway tab to view only Halfbill models.

You can also toggle the Thinking option (On/Off) at the bottom depending on the model's capabilities.

For example, type gpt-5.5 to find that model, select it, and press Enter.

Start Coding

All set! Kimi Code is now configured. Your requests are routed through Halfbill, and usage and cost statistics appear in your Halfbill dashboard.

Use /model in the terminal session at any time to switch models.

Manual Configuration (Advanced)

If you prefer to configure your environment manually without using the interactive provider manager, you can write settings directly to your configuration file at ~/.kimi-code/config.toml (or C:\Users\<YourUsername>\.kimi-code\config.toml on Windows).

Here is an example TOML configuration that registers GPT-5.5, Claude Sonnet 5, and Claude Opus 5 manually:

default_model = "llmgateway/gpt-5.5"

[providers.llmgateway]
type = "openai"
api_key = "llmgtwy_your_api_key_here"
base_url = "https://api.halfbill.uk/v1"

[models."llmgateway/gpt-5.5"]
provider = "llmgateway"
model = "gpt-5.5"
max_context_size = 400000
max_output_size = 128000
capabilities = [ "image_in", "thinking", "tool_use" ]
display_name = "GPT-5.5"

[models."llmgateway/claude-sonnet-5"]
provider = "llmgateway"
model = "claude-sonnet-5"
max_context_size = 200000
max_output_size = 32000
capabilities = [ "image_in", "thinking", "tool_use" ]
display_name = "Claude Sonnet 5"

[models."llmgateway/claude-opus-5"]
provider = "llmgateway"
model = "claude-opus-5"
max_context_size = 200000
max_output_size = 32000
capabilities = [ "image_in", "thinking", "tool_use" ]
display_name = "Claude Opus 5"

Why Use Halfbill with Kimi Code CLI

• Claude and GPT — Anthropic and OpenAI models at half list price in a single CLI configuration.
• Unified cost tracking — Get a detailed breakdown of costs per prompt and session in your dashboard.
• Response caching — Automatically cache repeated requests (such as parsing or building commands) to save API costs.