Models listed
4
Published in this category
Worth weighing up
What goes in and out, licence terms, and whether you can host it yourself
How we treat data
Published specs only — we don't estimate numbers a vendor hasn't stated
Dedicated moderation classifiers for text and supported image inputs. Test policy decisions, false positives and missed cases.
Scan the table below, then open any model for pricing, limits and the full write-up.
| Shieldstral 1.0 Mistral AI | 19.7 | 32K | — | — | — |
| GPT OSS Safeguard 120B OpenAI | 56.4 | 131.07K | $0.15 | $0.60 | — |
| GPT OSS Safeguard 20B OpenAI | — | 131.07K | — | — | — |
| Llama-Guard-3-8B Meta | — | 128K | — | — | — |
1–4 of 4 models · select a column to sort
About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.