Back to all models

omni-moderation-2024-09-26

OpenAI · omni-moderation

Available
Latest in family

Key Metrics

Input Limit

N/A tokens

Output Limit

N/A tokens

Input Cost

$0.00/1M

Output Cost

$0.00/1M

Sample API Code

Required Libraries

Notes

Snapshot version of omni-moderation, released on 2024-09-26. Snapshots let you lock in a specific version of the model so that performance and behavior remain consistent. Endpoints: v1/moderations. Performance: High. Speed: Medium.

Capabilities

harmful content detection
text moderation
image moderation
version locking

Supported Data Types

Input Types

text
image

Output Types

text

Strengths & Weaknesses

Exceptional at

consistent performance and behavior (due to snapshotting)
most capable moderation model (as of 2024-09-26)
detecting harmful content in text (as of 2024-09-26)
detecting harmful content in images (as of 2024-09-26)
high performance (as of 2024-09-26)

Good at

medium speed (as of 2024-09-26)

Additional Information

Latest Update

Sep 26, 2024

Knowledge Cutoff