Promote Sign in Sign up

AI evaluation

Selene 1

AI evaluation models to test and improve generative AI applications.

Source rating 5.0 (79) 484 views 484/mo traffic 0 saves Freemium
AI evaluation LLM-as-a-Judge Generative AI
More categories (4)
Model evaluation Prompt testing AI Quality AI security
Visit website Sign in to save

Free + from $10 / 1K API calls (Selene), $3 / 1K API calls (Selene Mini) after free credits / monthly

Verdict

A quick read before you dig into the full page.

Best if
AI evaluation models to test and improve generative AI applications
Skip if
You need enterprise SLAs or a fully managed team plan right away
Pick this when
Freemium · Free + from $10 / 1K API calls (Selene), $3 / 1K API calls (Selene Mini) after free credits / monthly

Overview

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.

Selene 1 screenshot

Access & connections

Where you can use Selene 1.

API

Public API available

Browse other tools with an API

Capabilities

What this tool accepts, produces, and is strongest at.

Highlights

  • 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 5

What is Atla?
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 Atla?
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).
What are Selene models?
Selene models are Atla's frontier AI evaluation models designed to provide precise judgments on your AI app’s performance. They are accurate LLM Judges on the market.
What is Eval Copilot?
Eval Copilot (beta) allows you to customize your evals, format your score as you wish, and fit eval criteria to your use case with few-shots.
What kind of support do you offer?
Atla offers support through Community Discord, Shared Slack channel, and Support SLA, depending on the pricing plan.
Selene 1 Free + from $10 / 1K API calls (Selene), $3 / 1K API calls (Selene Mini) after free credits / monthly
Visit website