For AI agents: step-by-step setup guide — /docs/agents.md, documentation index — /llms.txt.

For AI agents

How to hand off integration to an AI agent: a ready-made prompt for any tool. Below — machine-readable documentation addresses and a skill the agent installs with a single command.

Send this prompt to your AI agent. It will set up the tool following the instructions below and ask you for the key.

Connect your tool to JoinGonka Gateway — the OpenAI- and Anthropic-compatible API of the Gonka network — following the instructions at https://gate.joingonka.ai/docs/agents.md. I'll provide the key myself: don't save it in repository files and don't modify global environment variables. At the end, verify the connection with a short request and report the result.

Below are the instructions themselves. The agent receives them as Markdown at /docs/agents.md.

• The API key is created by a human — in the dashboard at gate.joingonka.ai. Don't register an account or create keys yourself: ask the user for a key.
• Keep the key in the JOINGONKA_API_KEY environment variable of your terminal session. Don't write it to files tracked by git, don't commit it, and don't print it in the report.
• Don't change the global OPENAI_* and ANTHROPIC_* variables — neither in the shell profile nor system-wide: other tools of the user read them. The key and URL are written to the tool's own config — that's what the installer does.

• Base URL for OpenAI API clients: https://gate.joingonka.ai/v1Copy
• Base URL for Anthropic API clients, without /v1: https://gate.joingonka.aiCopy
• The key is passed in the Authorization: Bearer jg-… or x-api-key: jg-… header
• The key for model requests starts with jg-; the management key gm- doesn't grant access to models.
• Recommended model: MiniMaxAI/MiniMax-M2.7Copy
• List of available models: GET https://gate.joingonka.ai/v1/models
• Per key — up to 120 requests per minute; over the limit you get a 429 response with the Retry-After header. Limits and timeouts are in the GET /v1/capabilities response, field limits.

Find the user's tool in the table at the end of the section. If there's a --tool value, configure it with the installer; if not, do it manually using the guide.

Via the installer#

One command, no questions: the key comes from an environment variable, the model from a flag. The installer writes the tool's config, saves a copy of the previous one, and verifies the connection with a request to the gateway.

JOINGONKA_API_KEY=<key> npx -y @joingonka/setup --tool <id> --model MiniMaxAI/MiniMax-M2.7 --non-interactive

If the tool was running, restart it: the config is read at startup.

Manually#

For a tool without an installer, open its guide (link in the table below) and set three values:

• base URL — https://gate.joingonka.ai/v1 for OpenAI API clients or https://gate.joingonka.ai for Anthropic API clients;
• key — in the API key field in the tool's settings;
• model — MiniMaxAI/MiniMax-M2.7 or another one from GET /v1/models.

Tools and guides#

Verify the key with a balance request: it doesn't spend tokens, and the key is taken from JOINGONKA_API_KEY:

curl -s https://gate.joingonka.ai/api/balance \
  -H "Authorization: Bearer $JOINGONKA_API_KEY"

Verify the URL, key, and model with a short request to the model:

curl -s https://gate.joingonka.ai/v1/chat/completions \
  -H "Authorization: Bearer $JOINGONKA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "MiniMaxAI/MiniMax-M2.7", "messages": [{"role": "user", "content": "Say OK"}], "max_tokens": 32}'

A 200 response with the model's text means the connection works. The installer runs this check itself: after it, exit code 0 is enough.

The error arrives in the error field of the response body — with the type and the reason text.

All response codes and limits are in the Errors & Rate Limits section.

At the end, tell the user:

• which tool was configured and which config file was written (the installer prints the path, with a copy of the previous one next to it);
• the base URL and model ID;
• the check result: the response code and the model's reply — or why the check couldn't be performed;
• what the user still needs to do themselves: for example, restart the tool or top up their balance.

Do not include the key in the report.

The instructions can be installed as a skill for your agent — then it's always at hand, no prompt needed:

npx skills add https://gate.joingonka.ai