Roo Code + Gonka AI — Autonomous AI Agent in VS Code

Roo Code is an autonomous AI agent for VS Code: it reads and edits files, runs commands in the terminal, works with the browser, and completes multi-step development tasks. It's a fork of Cline that goes further: customizable work modes (Architect, Code, Ask, Debug, and custom), custom project-specific instructions, and a flexible model settings panel. Essentially, it's an entire team of AI specialists inside your editor.

The main problem with such agents is token consumption. For a single task, Roo Code processes file contexts, command outputs, and tool results—this can be tens of millions of tokens. At Anthropic's prices ($3-15 per 1M), one full session turns into $30-1500. For daily work, this is unrealistic.

JoinGonka Gateway reduces costs thousands of times: the same session will cost $0.01-1.00. The Gateway resells inference from the decentralized Gonka network and supports both the OpenAI format (provider "OpenAI Compatible") and the Anthropic format (endpoint /v1/messages)—Roo Code connects via either of the two. This transforms Roo Code from an expensive demonstration into a daily working tool.

Step 1: Install Roo Code and get a key

Installing Roo Code: in VS Code open Extensions (Ctrl/Cmd+Shift+X), search for "Roo Code" and click Install. After installation, the kangaroo icon for Roo Code will appear in the sidebar.

JoinGonka API Key: if you don't have a key yet — register at gate.joingonka.ai/register, get 3M free tokens and create a key with the jg- prefix in Dashboard.

Step 2: Configure Roo Code (OpenAI Compatible)

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

npx @joingonka/setup --tool roo

The installer is universal (if no flag is provided, it will ask you to select a tool from the list), it will ask for your jg-… key, and after configuration, it performs a live verification by sending a request to the gateway. It does not touch other settings. Below is the manual method if you prefer to set it up yourself.

Manual setup (Plan B)

Open the Roo Code panel and go to settings (gear icon). In the provider section, set the following:

API Provider — select OpenAI Compatible.
Base URL — https://gate.joingonka.ai/v1
API Key — jg-your-key
Model (Model ID) — MiniMaxAI/MiniMax-M2.7

Below, in the Model Configuration block, you can manually refine the model parameters:

Context Window — 200000 (200K tokens; DeepSeek V4 Flash has 380000).
Max Output Tokens — 8192 for MiniMax M2.7 and GLM-5.3 Flash, 32768 for DeepSeek V4 Flash.
Input Price / Output Price — you can enter the real rates (≈$0.0069 per 1M input, output ×3) so that Roo Code can correctly calculate task costs directly in the interface.

Important note on tool calling: Roo Code uses only native tool calling — there is no XML fallback as in older agents. Therefore, the model must be capable of function calling. Models in our network via our Gateway support native tool calling — Roo Code works with them out of the box.

Verification: in the Roo Code chat, type «Create a file named hello.py with a function that prints Hello World». The agent will offer to create the file and show a diff for you to approve.

Comparing Agent Session Costs

Roo Code is an agentic tool: it doesn't just respond with a message, it completes a task — reads files, writes code, runs tests, fixes errors. Each action is a model call. Let's compare the cost of typical sessions:

Task	Tokens	Anthropic Claude	OpenAI GPT	JoinGonka Gonka
Simple bug-fix	~5M	$15 — $75	$12 — $50	$0.048
New feature (2-3 files)	~20M	$60 — $300	$50 — $200	$0.19
Refactoring module	~50M	$150 — $750	$125 — $500	$0.48
Full dev session (4h)	~100M	$300 — $1,500	$250 — $1,000	$0.96

With JoinGonka Gateway, Roo Code becomes a daily tool — you can run it for every ticket, every bug, every feature, without worrying about the bill. 3M free tokens at the start allow you to try the combo without a card.

Model parameters (all have 200K context): all network models provide up to 8192 response tokens. If max_tokens for a non-stream request is not specified, the Gateway defaults to returning up to 1500 tokens. Roo Code automatically breaks down long generations into steps.

How Roo Code differs from Cline: modes and Anthropic format

Roo Code is a fork of Cline, but with notable differences that change the workflow:

Modes: switch the agent's role depending on the task — Architect for planning, Code for coding, Ask for project-related questions, Debug for finding issues. You can create custom modes with separate instructions and a set of allowed tools.
Native tool calling only: unlike agents with text/XML parsing, Roo Code sends tools using the native OpenAI tools schema and receives calls as separate events — lower latency and more reliable results. The downside: the model must support function calling (network models via our Gateway do support this).
Custom instructions and profiles: project-level rules (e.g., via a rules file in the repository) and multiple saved provider configurations that are easy to switch between.

Connecting via Anthropic-format. If you want to use our /v1/messages endpoint instead of the OpenAI format: in settings select API Provider → Anthropic, check «Use custom base URL» and specify https://gate.joingonka.ai, in the Anthropic API Key field insert the same jg-your-key, then set the model name (e.g., MiniMaxAI/MiniMax-M2.7). The key and balance are shared for both formats; native tool_use in Anthropic mode also passes through the Gateway.

Roo Code + Gonka = an autonomous AI agent in VS Code with modes and native tool calling for pennies. A development session costs $0.10 instead of $300-1,500 with Anthropic, and the starting tokens allow you to try it without a card.

← Kilo Code + Gonka AI — AI-Agent in VS Code LlamaIndex + Gonka AI — RAG applications for pennies →

Want to learn more?

Explore other sections or start earning GNK right now.

Get free tokens →