Selene 1
AI evaluation models to test and improve generative AI applications.
Social Media
Selene 1 Introduction
What is Selene 1?
Atla provides frontier AI evaluation models to evaluate generative AI, find and fix AI mistakes at scale, and build more reliable GenAI applications. It offers an LLM-as-a-Judge to test and evaluate prompts and model versions. Atla's Selene models provide precise judgments on AI app performance, running evals with accurate LLM Judges. They offer solutions optimized for speed and industry-leading accuracy, customizable to specific use cases with accurate scores and actionable critiques.
How to use Selene 1?
Use Atla's Selene eval API to evaluate outputs and test prompts and models. Integrate the API into existing workflows to generate accurate eval scores with actionable critiques. Customize evals with few-shots in the Eval Copilot (beta).
Why Choose Selene 1?
Choosing this means you get a powerful platform that helps you build and manage AI projects with ease, even if you’re just starting out.
Selene 1 Features
AI API
- ✓LLM-as-a-Judge for evaluating AI models
- ✓Selene models for precise AI evaluation
- ✓Eval Copilot for customizing evaluation criteria
- ✓API access for integration into existing workflows
- ✓Actionable critiques and accurate scores
FAQ?
Pricing
Free
1,000 free API calls (Selene), 3,333 free API calls (Selene Mini) per month
Pro
Designed for startups with AI applications in production
Enterprise
Designed for teams with more security, deployment, and support needs
