Catsu Documentation

A unified Python client for embedding APIs

Catsu is a unified Python client for accessing multiple embedding providers through a single, consistent API. It supports 11 major embedding providers with over 50 models, providing:

• Unified Interface: Single API for all providers
• Automatic Retry Logic: Built-in exponential backoff
• Cost Tracking: Automatic usage and cost calculation
• Local Tokenization: Count tokens without API calls
• Type Safety: Full type hints and validation
• Async Support: Both sync and async methods

Quick Example

import catsu

# Initialize the client
client = catsu.Client()

# Generate embeddings (auto-detects provider from model name)
response = client.embed(
    model="voyage-3",
    input="Hello, embeddings!"
)

# Access your results
print(f"Dimensions: {response.dimensions}")
print(f"Tokens used: {response.usage.tokens}")
print(f"Cost: ${response.usage.cost:.6f}")

Get Started

Why Catsu?

The world of embedding API clients is fragmented. Catsu provides a clean, consistent interface across all major providers while handling the complexity of retries, error handling, and cost tracking for you.

Ready to get started? Head to the Installation page!