Access 10+ AI models through a single API endpoint. From lightweight to 1-trillion-parameter coding models. No OpenAI key needed.
| Model | Parameters | Best For | Speed | Context |
|---|---|---|---|---|
| kimi-k2.7-code:cloud Flagship | 1T | Coding, code review, debugging | Medium | 256K |
| mistral-large-3:675b-cloud | 675B | General purpose, reasoning | Medium | 128K |
| qwen3.5:397b-cloud | 397B | Multilingual, chat | Medium | 128K |
| deepseek-v4-pro:cloud New | — | Reasoning, analysis, math | Medium | 128K |
| glm-5.2:cloud | — | General purpose, fast chat | Fast | 128K |
| gemma4:31b-cloud Fast | 31B | Lightweight, quick responses | Fast | 8K |
| minimax-m2.7:cloud | — | Creative writing, multimodal | Fast | 245K |
| gpt-oss:120b-cloud | 120B | Open-source GPT alternative | Medium | 128K |
| deepseek-v4-flash:cloud Fast | — | Fast reasoning, coding | Fast | 128K |
| kimi-k2.6:cloud | — | Balanced coding + chat | Fast | 256K |
No OpenAI/Anthropic key required. Use your own API key.
10+ models from different providers in one API.
Pay with bunq (EU) or BTC/ETH/USDC (global).
Cloud-backed inference with sub-second response times.
Self-hosted infrastructure. No data sold to third parties.
Drop-in replacement for OpenAI API format.
# 1. Log in (or create an account) at https://webx11.duckdns.org/dashboard.html # 2. Come back here — this box reads your session and creates a key: POST https://webx11.duckdns.org/api/apikeys Authorization: Bearer <your session token> { "name": "my-app" } → 201 { "key": "wx11_..." } # shown once — save it!
⚠️ Requires a paid plan (Pro €9.99/mo or higher). Your key is shown once — store it securely. Daily limits apply per plan.
🔒 Instant activation: subscription plans unlock immediately, digital products show their download link.
# Chat completion — OpenAI-compatible format curl -X POST https://webx11.duckdns.org/ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer wx11_your_api_key" \ -d '{ "model": "kimi-k2.7-code:cloud", "messages": [ {"role": "system", "content": "You are a helpful coding assistant."}, {"role": "user", "content": "Write a Python function to reverse a linked list."} ], "stream": false }'
import requests response = requests.post( "https://webx11.duckdns.org/ai/v1/chat/completions", headers={ "Authorization": "Bearer wx11_your_api_key", "Content-Type": "application/json" }, json={ "model": "kimi-k2.7-code:cloud", "messages": [{"role": "user", "content": "Hello!"}], "stream": False } ) print(response.json()["message"]["content"])
const response = await fetch("https://webx11.duckdns.org/ai/v1/chat/completions", { method: "POST", headers: { "Authorization": "Bearer wx11_your_api_key", "Content-Type": "application/json" }, body: JSON.stringify({ model: "gemma4:31b-cloud", messages: [{ role: "user", content: "Summarize this article." }], stream: false }) }); const data = await response.json(); console.log(data.message.content);
# Coding & reasoning kimi-k2.7-code:cloud # 1T-class coding model deepseek-v4-pro:cloud # DeepSeek V4 Pro deepseek-v4-flash:cloud # Fast, cheap, default gpt-oss:120b-cloud # OpenAI open-source 120B # General chat glm-5.2:cloud # GLM 5.2 qwen3.5:397b-cloud # Qwen 3.5 397B mistral-large-3:675b-cloud# Mistral Large 3 gemma4:31b-cloud # Gemini-family 31B minimax-m2.7:cloud # MiniMax M2.7 minimax-m3:cloud # MiniMax M3 kimi-k2.6:cloud # Kimi K2.6 # Local (fast, no cloud cost) llama3.2:latest # Local Llama 3.2 coder:latest # Local coding model
X-RateLimit-Limit: 1000 # Total requests per month X-RateLimit-Remaining: 987 # Remaining this month X-RateLimit-Reset: 1690000000 # Unix timestamp when limit resets