Gateway Status
Real-Time System Health & Metrics
System Health
Loading system status...
Available Models
Loading models...
Gateway Configuration
API Keys, Tokens & Authentication
Compatibility Models
Enable compatibility mappings and advertise fake models (GPT, Claude, Gemini, DeepSeek) routing to Qwen.
🪣 Qwen Token Pool
The gateway rotates between multiple Qwen tokens automatically.
Tokens are added by token_refresher.py daily,
or manually below.
Runtime
Anti-Abuse
Token Economy
Hourly usage is charged as billed tokens. Raw prompt/completion totals remain visible as statistics.
Model Mappings
⚠️ Mappings Inactive: Compatibility / Fake models are currently disabled. Client requests for mapped models (like GPT/Claude) will not be routed.
Loading mappings...
Visual Model Mapper
Drag & Drop Interface for Model Routing
⚠️ Mappings Inactive: Compatibility / Fake models are currently disabled. Visual connections represent inactive mappings.
Tip: Drag blocks to reorganize. Click a block to edit its mapping. Connections show how client models route to Qwen models.
User Profile
Personal settings, API key and token usage
Account Info
API Credentials
Use these API keys in your code to authenticate requests. Do not share your API keys.
Token Consumption
Total token usage across all API requests made with your credentials.
Users Management
Monitor User Statistics, Hourly Limits, and Ban Accounts
Token Consumption
Request Counts
Registered Users
Loading users...
API Playground
Test Your Gateway Endpoints
Chat Completion Test
Response
cURL Example
Integration Settings
Quick Connection Guide & Base URL
API Base URL
cURL Integration
curl https://aivanta.qzz.io/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello, world!"}],
"temperature": 0.7
}'
Python Integration
from openai import OpenAI
client = OpenAI(
base_url="https://aivanta.qzz.io/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "user", "content": "Hello, world!"}
],
temperature=0.7
)
print(response.choices[0].message.content)
Node.js Integration
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "https://aivanta.qzz.io/v1",
apiKey: "YOUR_API_KEY",
});
async function main() {
const completion = await openai.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "Hello, world!" }],
temperature: 0.7,
});
console.log(completion.choices[0].message.content);
}
main();
Go Integration
package main
import (
"context"
"fmt"
"log"
"github.com/sashabaranov/go-openai"
)
func main() {
config := openai.DefaultConfig("YOUR_API_KEY")
config.BaseURL = "https://aivanta.qzz.io/v1"
client := openai.NewClientWithConfig(config)
resp, err := client.CreateChatCompletion(
context.Background(),
openai.ChatCompletionRequest{
Model: "gpt-4o",
Messages: []openai.ChatCompletionMessage{
{
Role: openai.ChatMessageRoleUser,
Content: "Hello, world!",
},
},
Temperature: 0.7,
},
)
if err != nil {
log.Fatalf("Completion error: %v", err)
}
fmt.Println(resp.Choices[0].Message.Content)
}
Python Integration (Streaming)
from openai import OpenAI
client = OpenAI(
base_url="https://aivanta.qzz.io/v1",
api_key="YOUR_API_KEY"
)
stream = client.chat.completions.create(
model="qwen3.6-plus",
messages=[
{"role": "user", "content": "Explain recursion in one short paragraph."}
],
stream=True
)
for chunk in stream:
content = chunk.choices[0].delta.content
if content:
print(content, end="", flush=True)
Python Integration (Tool Calling)
from openai import OpenAI
import json
client = OpenAI(
base_url="https://aivanta.qzz.io/v1",
api_key="YOUR_API_KEY"
)
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "The city and state, e.g. Kyiv, Ukraine"},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
},
"required": ["location"]
}
}
}
]
response = client.chat.completions.create(
model="qwen3.6-plus",
messages=[
{"role": "user", "content": "What is the weather in Kyiv right now?"}
],
tools=tools,
tool_choice="auto"
)
message = response.choices[0].message
if message.tool_calls:
for tool_call in message.tool_calls:
print(f"Function called: {tool_call.function.name}")
print(f"Arguments: {tool_call.function.arguments}")
else:
print(f"Response: {message.content}")