4 min

LLM APIs in 4 minutes

OpenAI, Anthropic, Google — same shape, three vendors.

Every coding assistant, every agent, every custom tool you'd build talks to an LLM API. Three big vendors, plus aggregators. Same shape.

The same call, three vendors

OpenAI

from openai import OpenAI
client = OpenAI()  # reads OPENAI_API_KEY

reply = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Say hello."}],
)
print(reply.choices[0].message.content)

Anthropic

from anthropic import Anthropic
client = Anthropic()  # reads ANTHROPIC_API_KEY

reply = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=256,
    messages=[{"role": "user", "content": "Say hello."}],
)
print(reply.content[0].text)

Google Gemini

from google import genai
client = genai.Client()  # reads GEMINI_API_KEY

reply = client.models.generate_content(
    model="gemini-3-pro",
    contents="Say hello.",
)
print(reply.text)

Or: one key, any model (OpenRouter)

OpenRouter proxies hundreds of models from every vendor behind a single OpenAI-compatible API. Useful when you want to A/B-test models, or when you don't want vendor lock-in.

from openai import OpenAI  # OpenAI-compatible
client = OpenAI(base_url="https://openrouter.ai/api/v1",
                api_key="sk-or-…")

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-6",   # any model from any provider
    messages=[{"role": "user", "content": "Say hello."}],
)

Where to get keys