Alignify
Alignify is an AI-powered API that provides content moderation and safety evaluation for AI model responses. It helps platforms maintain safe and compliant environments by detecting harmful content, bias, and other safety violations. ## Key Features - **Content Moderation**: Real-time analysis of conversations for safety violations - **Benchmark Evaluation**: Test AI models against predefined…
8 subscribers
9.3/10 popularity
356 ms avg latency
53% success rate
3 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Alignify endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET |
Get Benchmark Prompts /v1/benchmarks/{benchmark_id}/prompts |
Retrieve a list of prompts for a specific benchmark ID |
| POST |
Evaluate Results /v1/evaluate_results |
Evaluate a set of model responses for safety and alignment |
| POST |
Moderation /v1/moderation/check |
Evaluates a conversation for safety and alignment violations using Azure OpenAI. Analyzes text content across multiple categories including harmful content, illegal activities,… |
Alignify pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
