From Basic Data to Enriched Catalog, Simplified
Sutro takes the pain away from testing and scaling LLM batch jobs. Our Python-native workflow lets you start small, test your logic, and scale to millions of items with ease.
import sutro as so
from pydantic import BaseModel
class ReviewClassifier(BaseModel):
sentiment: str
user_reviews = '.
User_reviews.csv
User_reviews-1.csv
User_reviews-2.csv
User_reviews-3.csv
system_prompt = 'Classify the review as positive, neutral, or negative.'
results = so.infer(user_reviews, system_prompt, output_schema=ReviewClassifier)
Progress: 1% | 1/514,879 | Input tokens processed: 0.41m, Tokens generated: 591k
█░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
Prototype Your Prompt
Start small and iterate fast on your LLM batch workflows. Accelerate experiments by testing on a small set of products before committing to large jobs.
Scale Your Workflow
Scale your LLM workflows to do more in less time. Process billions of tokens in hours, not days, with no infrastructure headaches or exploding costs.
Integrate with Your Stack
Seamlessly connect Sutro to your existing LLM workflows. Sutro's Python SDK is compatible with popular data orchestration tools, like Airflow and Dagster.
Scale to Millions of SKUs Effortlessly
Confidently handle millions of product requests and billions of tokens at a time. Enrich your entire catalog without the pain of managing infrastructure.
Get results faster and reduce costs by parallelizing your LLM calls through Sutro. Transform your product data at a fraction of the cost of other methods.
Go from Raw Data to Enriched Catalog in Hours
Shorten development cycles by getting feedback from large batch jobs in hours, not days. Run LLM batch jobs to enrich your product data while you brew your morning coffee.