Azure AI Evaluation SDK (Microsoft Foundry)
previewPython SDK from Microsoft Foundry for scoring generative AI app outputs locally with quality, RAG, agent and safety evaluators.
By Microsoft · learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk
Package download activity
Each package is shown on its own; packages that can be installed together are never added up. Week 2026-W40 (2026-09-28 to 2026-10-04).
PyPIazure-ai-evaluation · headline (ranked)
33,482 downloads in the week, -4.5% vs prior week · rank 23 on PyPI
Reproduce this number (ClickHouse SQL) · registry metadata (mapping checked 2026-10-07)
GitHub stars
No public repository is linked from Azure AI Evaluation SDK (Microsoft Foundry)'s own site. This is not a zero.
Facts
| Categories | Evaluation | |
|---|---|---|
| Status | Preview | |
| Licence | MIT | source, checked 2026-10-07 |
| Self-host | Yes | source, checked 2026-10-07 |
| OpenTelemetry | Unknown | source, checked 2026-10-07 |
| Pricing model | usage | |
| Entry price | not published in USD; SDK is MIT-licensed and free; safety, red-teaming and playground evaluations are metered at $20 per 1M input tokens and $60 per 1M output tokens; quality evaluations are billed as tokens on your own judge model deployment with no surcharge. Prices rendered via chromium. | source, checked 2026-10-07 |
| Free tier | Yes | |
| Measurability | Measured (mapped SDK packages) |
Facts last verified 2026-10-07 on first-party pages. Prices as published, taxes excluded; non-USD prices are not converted.
Compare
Spotted an outdated fact? The methodology page explains how facts are checked; corrections are applied at the next weekly build.