text-moderation-latest
text-moderation-latest is OpenAI's leftover text-only moderation alias, not a 2026 safety default. Rechecked 2026-08-18: platform.openai.com/docs/guides/moderation still lists the leftover text-moderation-* family and now points people at omni-moderation-*. The still-listed omni alias on this site is omni-moderation-latest, with dated twin omni-moderation-2024-09-26. Drop leftover future best default / latest safety path / unaudited free crown.
Compare Llama Guard 3 if you wanted another leftover safety snapshot (live Meta card is Llama Guard 4 12B).
Key Features
- Previous text-only alias: Leftover copy already admitted omni-moderation would replace it. Recheck the Moderation guide before you hard-code
text-moderation-latest. - Not the 2026 safety lead: The live guide still lists omni-moderation as the multimodal path.
- No invented free/latency row: Do not paste leftover "free forever / millisecond" unless the first-party page still says that on the day you quote it.
- Website is the guide, not api-keys: Recheck the Moderation guide, not the keys page.
Use Cases
- People with a text-moderation-latest bookmark who need the catalog corrected.
- People comparing leftover text-moderation vs still-listed omni-moderation.
- People who were about to keep a text-only OpenAI safety stack as the 2026 default.
Limitation: We did not send sample text through the Moderation endpoint.
Pricing
First-party pages on 2026-08-18.
| Piece | Price | Notes |
|---|---|---|
| text-moderation-latest | Leftover text-only alias | Recheck the Moderation guide. |
| omni-moderation-latest | Still-listed alias | omni-moderation-latest is the later leftover on this site. |
| Dollar / free row | Recheck live docs | Do not invent a 2026 free or per-call census. |
If a leftover blog still treats text-moderation as the current OpenAI default, treat the omni card as the correction.
Getting Started
- Open the Moderation guide before you hard-code
text-moderation-latest. - Recheck omni-moderation-latest if you wanted the still-listed multimodal leftover.
- Recheck Llama Guard 3 if you wanted another leftover safety snapshot.
- Do not paste "future best default" into a 2026 deck as if it were still current.
Frequently Asked Questions
Is text-moderation-latest still the OpenAI default?
No. The live guide points people at omni-moderation.
Same as omni-moderation-latest?
No. omni-moderation-latest is the later leftover multimodal alias.
Is it free?
Recheck first-party docs. Do not invent a 2026 free census.
Alternatives
- omni-moderation-latest: Later leftover OpenAI moderation alias, still listed.
- Llama Guard 3: Leftover Meta safety snapshot; live card is Guard 4 12B.
- GPT-5.6 Sol: Live OpenAI frontier chat if you wandered here for a current model.
Tips
- Call
text-moderation-latesta leftover text-only alias, not a 2026 default. - Point new OpenAI moderation work at the live omni path on the guide.
- Recheck first-party docs before you invent a free or per-call price.
Conclusion
text-moderation-latest is a leftover text-only OpenAI alias, not the 2026 safety default. Start at platform.openai.com/docs/guides/moderation, then decide whether omni-moderation-latest already covers the path you need.
Comments
No comments yet. Be the first to comment!
Related Tools
omni-moderation-latest
platform.openai.com/docs/guides/moderation
Hosted OpenAI omni-moderation snapshot. Rechecked: still listed. Not the 2026 safety default path.
LLaMA Guard 3
www.llama.com
Previous Llama Guard snapshot. Rechecked: live card is Llama Guard 4 12B. Not the 2026 safety default.
Shap-e
github.com/openai/shap-e
Previous OpenAI Shap-E snapshot. Rechecked: leftover 2023 3D research card, not a 2026 image/3D default. Live stills path is GPT Image 2.
Related Insights

Grok Bot and Hermes Bot: one person finally gets a think tank and a secretariat
Grok Bot now ships with Cursor Pro+. Hermes Bot runs on a VPS. They are not smarter chat boxes. The think tank advises, the secretariat executes, and you still make the call.
Hook OpenCode Go into Codex on Windows. Do Not Open a Second Toolkit.
A ChatGPT-signed Codex desktop app still shows mostly GPT in the picker. On Windows, enable only OpenCode Go and the Grok, GLM, Kimi, DeepSeek, and MiniMax models you already pay for appear in the same selector. Keys stay local. Native GPT stays put.
What Locks Codex Is the Picker, Not the Models
You already pay for OpenCode Go, Grok, and Z.ai, but the Codex picker still shows mostly GPT. The community project codex-router does not teach another install ritual. It puts subscriptions you already bought back into the selector, keeps keys on the machine, and leaves native GPT alone.