Dashboard

Balance

0 GNK

API Keys

0

Total Spent

0 ngonka

Total Inferences

0

Chat

Start a conversation

API Keys

Transaction History

📚 API Documentation

Complete guide to using Gonka AI Gateway API

Getting Started

Gonka AI Gateway provides an OpenAI-compatible API with Web3 authentication and token-based billing.

Note: You need to authorize and create an API key before using the API.

Authentication

All API requests require authentication using an API key in the Authorization header:

Authorization: Bearer sk-your-api-key-here

Getting Your API Key

  1. Authorize on the dashboard
  2. Navigate to "API Keys" section
  3. Click "Create New API Key"
  4. Save the key immediately - it won't be shown again!

Base URL

The gateway is served over HTTPS (proxied via Traefik). All API requests should be made to:

https://gonka-gateway.mingles.ai/v1

API Endpoints

POST /chat/completions

Create a chat completion (OpenAI-compatible)

Request

POST /chat/completions
Content-Type: application/json
Authorization: Bearer sk-your-api-key

{
  "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  "messages": [
    {"role": "user", "content": "Hello!"}
  ],
  "stream": false
}

Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Streaming

To enable streaming, set "stream": true in the request:

{
  "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  "messages": [
    {"role": "user", "content": "Tell me a story"}
  ],
  "stream": true
}
GET /models

List available models

Request

GET /models
Authorization: Bearer sk-your-api-key

Response

{
  "object": "list",
  "data": [
    {
      "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
      "object": "model",
      "created": 1677610602,
      "owned_by": "gonka"
    }
  ]
}

Using with OpenAI Python SDK

The API is fully compatible with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(
  api_key="sk-your-api-key-here",
  base_url="https://gonka-gateway.mingles.ai/v1"
)

response = client.chat.completions.create(
  model="Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  messages=[
    {"role": "user", "content": "Hello!"}
  ]
)

print(response.choices[0].message.content)

Simple Python Example

Here's a simple example using Python's requests library:

import requests

url = "https://gonka-gateway.mingles.ai/v1/chat/completions"
headers = {
  "Authorization": "Bearer sk-your-api-key-here",
  "Content-Type": "application/json"
}
data = {
  "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  "messages": [
    {"role": "user", "content": "Hello! How are you?"}
  ]
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(result["choices"][0]["message"]["content"])

Using with curl

curl https://gonka-gateway.mingles.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Using with n8n

n8n Workflow Example: Check out this ready-to-use workflow at https://n8n.io/workflows/12114

Token Billing

Each API request consumes GNK tokens from your balance. Tokens are calculated from the API response and balance is automatically deducted after each request.

Pricing Note: We are currently in a trial period on the Gonka network. During this time, inference prices are very low - just tiny fractions of GNK tokens. Final pricing will be announced after the trial period ends.
Warning: If your balance is insufficient, the request will fail with a 402 Payment Required error.

Checking Your Balance

You can check your balance on the dashboard or via the API:

GET /api/user/balance
Authorization: Bearer sk-your-api-key

Rate Limits

Currently, there are no rate limits. However, please use the API responsibly.

Support

For issues or questions, please contact support or check the dashboard for your transaction history.

Connect to OpenClaw

Use this guide to connect OpenClaw to the Gonka gateway: configure the provider on your OpenClaw node, then use the OpenClaw Telegram bot commands to switch to the Gonka model and check status.

1. Provider config (OpenClaw node)

Configure the Gonka provider on your OpenClaw node/gateway so the agent can use Gonka models. Edit openclaw.json or your models.json (wherever OpenClaw reads models.providers).

Replace:

  • https://gonka-gateway.mingles.ai/v1 — with your gateway base URL if different.
  • sk-.......... — with your API key (from registration or dashboard).
{
  "models": {
    "providers": {
      "gonka": {
        "baseUrl": "https://gonka-gateway.mingles.ai/v1",
        "apiKey": "sk-..........",
        "auth": "api-key",
        "api": "openai-completions",
        "authHeader": true,
        "models": [
          {
            "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
            "name": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
            "api": "openai-completions",
            "reasoning": false,
            "input": ["text"],
            "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
            "contextWindow": 200000,
            "maxTokens": 8192
          }
        ]
      }
    }
  }
}

After editing: save the file and restart the OpenClaw gateway/node if it does not reload config automatically.

2. OpenClaw Telegram bot commands

These commands are used in the OpenClaw Telegram bot chat (not in the gateway config or API). They let you switch to the Gonka model and check that it is active.

/status

In the OpenClaw Telegram bot, send /status to see the current runtime state, including which model is in use.

🦞 OpenClaw 2026.2.15 (3fe22ea)
🧠 Model: gonka/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 · 🔑 api-key sk-dvg…6GIAPE (models.json)
🧮 Tokens: 18k in / 137 out
📚 Context: 18k/200k (9%) · 🧹 Compactions: 0
🧵 Session: agent:main:main • updated just now
⚙️ Runtime: direct · Think: off · verbose
🪢 Queue: collect (depth 0)

From this you can confirm that the Model line shows gonka/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 when the Gonka model is active.

/model <provider/model-id>

In the OpenClaw Telegram bot, send /model <provider/model-id> to switch the active model. To use the Gonka Qwen model, send:

/model gonka/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Example: you send /model gonka/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8, the agent replies Model set to gonka/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8. Then send /status again to verify the Model line shows the Gonka model.

3. Summary

What Where Action
Add Gonka provider OpenClaw node — openclaw.json or models config Put the models.providers.gonka block from section 1 into your config. Set baseUrl and apiKey.
Switch to Gonka model OpenClaw Telegram bot Send: /model gonka/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8
Check current model OpenClaw Telegram bot Send: /status — look at the Model line in the reply.

So: config = on the node; /status and /model = in the OpenClaw Telegram bot chat.