OpenAI-Compatible Proxy for Multi-Provider AI Models

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "os_hub_your_key_here",
  baseURL: "https://api.aimodelgate.ai/v1",
});

const response = await client.chat.completions.create({
  model: "oah/llama-3-70b",          // virtual model → smart-routed
  messages: [
    { role: "user", content: "Explain quantum computing" }
  ],
  max_tokens: 512,
});

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

// Response headers:
// x-dlp-latency:           12        (DLP scan time)
// x-request-id:            req_xxxx  (audit trail)
// x-modelgate-model:             llama-3-70b
// x-modelgate-provider:          groq

from openai import OpenAI

client = OpenAI(
    api_key="os_hub_your_key_here",
    base_url="https://api.aimodelgate.ai/v1",
)

response = client.chat.completions.create(
    model="oah/llama-3-70b",          # virtual model → smart-routed
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ],
    max_tokens=512,
)

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

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="oah/gpt-4.1-mini",
    openai_api_key="os_hub_your_key_here",
    openai_api_base="https://api.aimodelgate.ai/v1",
    max_tokens=512,
)

response = llm.invoke("Explain quantum computing")
print(response.content)

# All LangChain features work: chains, agents, tools, streaming.
# PII redaction and budget enforcement happen transparently.

curl -X POST https://api.aimodelgate.ai/v1/chat/completions \
  -H "Authorization: Bearer os_hub_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "oah/llama-3-70b",
    "messages": [
      {"role": "user", "content": "Explain quantum computing"}
    ],
    "max_tokens": 512
  }'

{
  "model": "oah/llama-3-70b",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "max_tokens": 256,
  "temperature": 0.7
}

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1709234567,
  "model": "oah/llama-3-70b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses quantum bits (qubits) instead of classical bits..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 87,
    "total_tokens": 99
  }
}