Prerequisites
Getting Started
Update your code
Point any OpenAI-compatible SDK to the each::labs base URL:from openai import OpenAI
client = OpenAI(
api_key="YOUR_EACHLABS_API_KEY",
base_url="https://api.eachlabs.ai/v1"
)
Make your first request
Use the provider/model-name format to pick any model:response = client.chat.completions.create(
model="openai/gpt-4o",
messages=[
{"role": "user", "content": "What is the capital of France?"}
]
)
print(response.choices[0].message.content)
Switch Models Instantly
Just change the model parameter. That’s literally it. No config changes, no new SDKs, no drama:
# Use Anthropic Claude
response = client.chat.completions.create(
model="anthropic/claude-sonnet-4-20250514",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
# Use Google Gemini
response = client.chat.completions.create(
model="google/gemini-2.5-pro-preview-06-05",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
# Use DeepSeek
response = client.chat.completions.create(
model="deepseek/deepseek-r1",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
Streaming
Streaming is not supported yet. Yeah, we know. It’s painful. We’re on it and it’ll be here soon. For now all requests return the complete response at once.
# Coming soon
stream = client.chat.completions.create(
model="openai/gpt-4o",
messages=[{"role": "user", "content": "Write a haiku about coding"}],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")
Advanced Features
LLM Router comes with some nice tricks out of the box:
- Smart Routing automatically sends requests to the cheapest or fastest provider
- Fallbacks so your app doesn’t break when a model is having a bad day
- Caching to save you money and time on repeated requests
- Rate Limiting per model or per user, your call
- Usage Analytics to keep tabs on costs, tokens, and latency
Next Steps
