Kilo Code + Gonka AI — AI-Agent in VS Code

Kilo Code is an open-source AI agent extension for VS Code that autonomously writes and edits code, runs terminal commands, and reads and fixes dozens of files at once. The project combines the strengths of Cline and Roo Code and is evolving as a unified agent platform: in addition to the IDE extension, there are options for JetBrains and CLI. The key feature is modes (agents): Code (writes code), Plan (also known as Architect — plans architecture without edits), Debug (finds the causes of errors), and Ask (answers project-related questions). You can also create your own modes.

The problem is the same as with any agent — token consumption. Kilo Code sends file context, command output, and step history to the model; a single task can easily consume 10-100M tokens. At Anthropic prices ($3-15 per 1M), this amounts to $30-1500 per session — impractical for everyday use.

JoinGonka Gateway reduces the cost hundreds and thousands of times: the same session costs $0.01-1.00. Since Kilo Code is open-source and supports any OpenAI-compatible endpoint (as well as Anthropic-format with a custom base URL), connecting our gateway is a matter of a single setting. This transforms Kilo Code from an expensive demonstration into an everyday tool.

Step 1: Install Kilo Code and Get Your Key

Install Kilo Code: In VS Code, open Extensions (Ctrl+Shift+X), search for "Kilo Code" and click Install. After installation, the Kilo Code icon will appear in the sidebar. The extension is also available on Open VSX for builds without the Marketplace.

JoinGonka API key: If you don't have an account yet — register at gate.joingonka.ai/register, get 10M free tokens and create a key with the jg- prefix in Dashboard → API Keys. The same key works for both OpenAI-format (/v1) and Anthropic-format (/v1/messages) — the balance is shared.

Step 2: Configure Kilo Code (OpenAI Compatible)

The easiest way is to set it up with a single-command installer. For CLI/file tools, it will automatically configure the JoinGonka provider (baseUrl, models), and for UI tools, it will display the required values for you to paste:

npx @joingonka/setup --tool kilo

The installer is universal (if no flag is provided, it will let you choose a tool from the list), will ask for your jg-… key, and will perform a live check via a request to the gateway after configuration. It does not touch other settings. Below is the manual method if you prefer to configure it yourself.

Configure manually (Plan B)

Open the Kilo Code panel and go to provider settings via the gear icon.

Method A — OpenAI Compatible (recommended). In modern versions of the extension, open Settings (gear icon) → Providers tab → click the Custom provider button at the bottom and fill in the dialog:

Provider ID: any identifier, e.g., joingonka.
Display name: e.g., JoinGonka Gonka.
Base URL: https://gate.joingonka.ai/v1
API key: jg-your-key
Models: add MiniMaxAI/MiniMax-M2.7. Kilo automatically fetches the list of models from the /v1/models endpoint — you can select a model from the list instead of entering it manually.

Click Submit — the models will appear in the picker. In the old interface (VSCode Legacy), the path is shorter: API Provider → OpenAI Compatible, then fill in the Base URL, API Key, and Model fields with the same values.

Method B — Anthropic format. Our gateway also responds to the Anthropic API. Select API Provider → Anthropic, enter your jg-your-key, check "Use custom base URL", and provide https://gate.joingonka.ai (without /v1 — Kilo will add /v1/messages itself).

Models and their output limits (both are available right now):

Model	Context	Max Output
moonshotai/Kimi-K2.6 (default)	200K	8192
MiniMaxAI/MiniMax-M2.7	200K	8192

In the custom provider dialog, you can set Max Output Tokens and Context Window for each model — set the values from the table for your chosen model.

Verification: in the Kilo Code chat, in Code mode, type "Create a file hello.py with a hello world function". The agent should offer a diff for approval and create the file. By default, Kilo Code requests confirmation before every action — this can be relaxed by allowing auto-execution for trusted operations.

Comparison of Agentic Session Costs

Kilo Code is an agentic tool: it doesn't just respond, it handles tasks from start to finish — reading files, writing code, running tests, and fixing bugs. Every step is an API call, and tokens accumulate quickly. Let's compare the costs of typical sessions via Anthropic Claude and our gateway to the Gonka network:

Task	Tokens	Anthropic Claude	JoinGonka Gonka
Simple bug fix	~5M	$15 — $75	$0.024
New feature (2–3 files)	~20M	$60 — $300	$0.096
Module refactoring	~50M	$150 — $750	$0.24
Full development session (4h)	~100M	$300 — $1,500	$0.48

Through JoinGonka Gateway, the input cost is ~$0.003 per 1M tokens, and output is roughly three times that — making it hundreds or thousands of times cheaper than Anthropic and OpenAI. Kilo Code becomes a daily tool: you can run it for every ticket, every bug, and every feature without checking the bill. With Anthropic prices, you would have to weigh every single run.

Model parameters: The network's models have a 200K token context window and a maximum output limit of 8192 tokens. Kilo Code might request more, but the gateway limits output to the model's upper ceiling (8192 for all network models). For long generations, the agent breaks the work into steps.

Modes and tool calling

A strength of Kilo Code is the modes (called 'modes' in the old extension and 'agents' in the new one), which you can switch between via a dropdown, the /agents command, or the Ctrl+. hotkey:

Plan / Architect — discuss and design a solution without touching files. Useful to run via the inexpensive Kimi K2.6: planning consumes a lot of context, and on our gateway, it costs pennies.
Code — the default mode: writes and edits code, applies diffs, runs commands.
Debug — purposefully searches for the root cause of a bug using logs and stack traces.
Ask — answers questions about the codebase without making changes.

The separate Orchestrator mode is deprecated in newer versions: agents with full tool access can now run subtasks (subagents) themselves without a dedicated orchestrator. Custom modes for your workflows are also supported.

Tool calling: our gateway forwards native OpenAI function calling and Anthropic tool_use, and the selected models (Kimi K2.6, MiniMax-M2.7) support tool invocation. This means that the Kilo Code agent loop—reading a file, editing, running a command, indexing the codebase—runs reliably on our models without brittle text-parsing of responses.

Kilo Code + Gonka = an open-source AI agent for VS Code with Plan/Code/Debug modes for pennies. A development session costs about $0.10 instead of $300-1500 with Anthropic, and 10M free tokens are enough for dozens of tasks.

← Hermes Agent + Gonka AI — Autonomous Agent for Pennies Roo Code + Gonka AI — Autonomous AI Agent in VS Code →

Want to learn more?

Explore other sections or start earning GNK right now.

Get 10M free tokens →