Call Claude, GPT and Gemini with One API Key: an OpenAI-Compatible Quickstart

Maintaining SDKs, keys and billing for several LLM vendors is the first tax every team pays when adopting AI. GetModel collapses all of it into one thing: one key + one OpenAI-compatible endpoint, models freely interchangeable.

Setup

1. Sign up and log in to the GetModel console;
2. Create a key (looks like sk-...) on the “API Tokens” page;
3. The endpoint is https://getmodel.ai/v1.

curl

curl https://getmodel.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-key" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{"role": "user", "content": "Explain an API gateway in one sentence"}]
  }'

To switch models, change only the model field — e.g. gpt-5.2 or gemini-3.0-pro; the request shape stays identical. See the pricing page for available models and live prices.

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-key",
    base_url="https://getmodel.ai/v1",
)

resp = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-key',
  baseURL: 'https://getmodel.ai/v1',
});

const resp = await client.chat.completions.create({
  model: 'gemini-3.0-pro',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(resp.choices[0].message.content);

Streaming

Add stream: true — the SSE format matches OpenAI exactly. For token usage, also pass stream_options: {"include_usage": true} and the final chunk carries the usage object.

stream = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Write a short poem about APIs"}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

FAQ

• Are native APIs supported too? Yes. Besides the OpenAI-compatible layer, Claude’s native /v1/messages, Gemini’s native API and others work with the same key.
• How does billing work? Pay per actual token usage of each model, from one shared balance; every request is itemized in the console logs.
• Rate limits? Enforced per key and per group — see your console for quotas. For production, enable client retries; the gateway already does multi-channel failover upstream.