Models/Collections/Best Moderation

Best Moderation

Moderation models that read a policy and return a verdict on the content you hand them, for text and in some cases images. Useful in front of a generation pipeline, in review queues, and anywhere the rules change per product or per customer instead of following a fixed list of categories.

Models

gpt-oss-safeguard-20b

compatible API

Open-weight safety classifier that judges content against the policy you write in the prompt

$0.07/ 1M tokensInput tokens
View

Shieldstral 1.0 3B

compatible API

Compact multimodal moderation model that judges text and images against your own policy

$0.09/ 1M tokensInput tokens
View

Open-weight alternatives

DeepSeek

DeepSeek-V4.1-Flash-1017

by DeepSeek

Multimodal 1M-context MoE checkpoint for coding, reasoning, and tool-using agents

$0.15 / 1M tokens · Input tokens
DeepSeek

DeepSeek-V4.1-Flash

by DeepSeek

Multimodal 1M-context MoE for efficient coding, reasoning, and long-horizon agent workflows

$0.15 / 1M tokens · Input tokens
Moonshot AI

Kimi K3

by Moonshot AI

Flagship multimodal reasoning LLM for long-horizon coding, knowledge work, and tool-rich agent workflows

$3.00 / 1M tokens · Input tokens
L

Laya

by Independent

Open-weight System 1 model for low-latency typed decisions without free-form generation

$0.02 / 1M tokens · Input tokens