⚡ LLM API Gateway Active

OpenAI-Compatible High-Availability Gateway for Google Gemini & Anthropic Claude Models

⚡ Interactive Swagger UI 📖 ReDoc Specs 📊 Status Dashboard 🔍 OpenAPI Schema

API Specifications & Configuration

Base URL

https://llm.wdsa.ru/v1

Authentication Header

Authorization: Bearer <YOUR_API_KEY>

Compatibility

100% OpenAI v1 API Standard

Supported Models

Pass any of the following model strings in your requests:

gemini-3.7-flash

Google DeepMind • Recommended

Next-generation Gemini 3.7 Flash with advanced reasoning, coding, and high speed.

gemini-3.6-flash

Google DeepMind

Fast, cost-effective multimodal model for high-throughput tasks.

claude-3-5-sonnet-20241022

Anthropic

Industry-leading performance for complex coding, analysis, and reasoning.

claude-3-5-haiku-20241022

Anthropic

Ultra-fast, lightweight model ideal for quick context processing.

API Endpoints

Method	Endpoint	Description
POST	`/v1/chat/completions`	Chat completions with streaming, function calling & thought signatures.
GET	`/v1/models`	List all supported models and specs.
POST	`/v1/embeddings`	Generate text embeddings.
POST	`/v1/images/generations`	Generate images using multimodal models.
GET	`/health`	Service health check status.
GET	`/status`	Real-time account capacity & KPI dashboard.

Integration Instructions & Examples

curl https://llm.wdsa.ru/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gemini-3.7-flash",
    "messages": [
      {"role": "user", "content": "Hello! Explain quantum computing in 2 sentences."}
    ],
    "temperature": 0.7,
    "stream": false
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.wdsa.ru/v1",
    api_key="YOUR_API_KEY"  # sec-...
)

response = client.chat.completions.create(
    model="gemini-3.7-flash",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a python function for binary search."}
    ]
)

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

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://llm.wdsa.ru/v1',
  apiKey: 'YOUR_API_KEY', // sec-...
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Hello!' }],
    model: 'gemini-3.7-flash',
  });

  console.log(completion.choices[0].message.content);
}

main();

{
  "providers": {
    "wdsa-llm": {
      "options": {
        "baseURL": "https://llm.wdsa.ru/v1",
        "apiKey": "YOUR_API_KEY"
      },
      "models": {
        "gemini-3.7-flash": { "name": "Gemini 3.7 Flash" },
        "claude-3-5-sonnet-20241022": { "name": "Claude 3.5 Sonnet" }
      }
    }
  }
}