> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zerogpu.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Moderation
> OpenAI-compatible content moderation, benchmarked against omni-moderation-latest.
Moderation models screen text for unsafe, harmful, or policy-sensitive content before it reaches your application or model workflow. Call either the [Responses API](/api-reference/responses) (`POST /v1/responses`) or the OpenAI-compatible [Chat Completions API](/api-reference/chat-completions) (`POST /v1/chat/completions`).
| Model | Input /1M | Output /1M | Params | Max tokens |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------: | ---------: | ------ | ---------: |
| 
zlm-v1-moderation-edge | \$0.02 | \$0.05 | 86M | 4,000 |
## zlm-v1-moderation-edge
> ZeroGPU's moderation model screens text for unsafe, harmful, or policy-sensitive content and returns the complete OpenAI 13-category taxonomy — a `flagged` verdict, per-category booleans, and calibrated `category_scores` — so it drops into any pipeline written against `omni-moderation-latest`. Under the hood it's an 86M-parameter DeBERTa encoder with a shared trunk feeding one binary safe/unsafe head and 13 category heads, with per-category thresholds calibrated on held-out validation data. In [head-to-head benchmarks](https://zerogpu.ai/benchmarks/moderation-edge) against OpenAI omni-moderation it wins the binary safe/unsafe decision (0.899 vs 0.853 F1) and 9 of 13 harm categories — with the largest gains on graphic violence, illicit content, and self-harm — while returning verdicts 1.2–1.8× faster at the median on production-range inputs, because inference is co-located at the edge instead of a round trip to a central API. Moderation sits inline in front of every response your app serves; this is the model that's fast and accurate enough to live there.
**References:** [Moderation benchmark](https://zerogpu.ai/benchmarks/moderation-edge) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
```bash Responses API theme={null}
curl https://api.zerogpu.ai/v1/responses \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"input": "I am so angry at this person that I want to hurt them. They are worthless and should be scared of what I might do next.",
"model": "zlm-v1-moderation-edge"
}'
```
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"model": "zlm-v1-moderation-edge",
"messages": [
{
"role": "user",
"content": "I am so angry at this person that I want to hurt them. They are worthless and should be scared of what I might do next."
}
]
}'
```
The API returns a standard completion envelope. The moderation verdict is inside it as an escaped JSON **string** — not a nested object — in `choices[].message.content` (Chat Completions) or `output[].content[].text` (Responses API). This is the actual, unmodified output:
```json Chat Completions theme={null}
{
"id": "20cb788a-ba05-4543-a2b3-e80f8e814e49",
"object": "chat.completion",
"created": 1786030403,
"model": "zlm-v1-moderation-edge",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "{\"model\":\"zlm-v1-moderation-edge\",\"results\":[{\"flagged\":true,\"unsafe_score\":1,\"categories\":{\"hate\":false,\"hate/threatening\":false,\"harassment\":true,\"harassment/threatening\":true,\"self-harm\":false,\"self-harm/intent\":false,\"self-harm/instructions\":false,\"sexual\":false,\"sexual/minors\":false,\"violence\":true,\"violence/graphic\":false,\"illicit\":true,\"illicit/violent\":true},\"category_scores\":{\"hate\":0.21574,\"hate/threatening\":0.168273,\"harassment\":0.82545,\"harassment/threatening\":0.957703,\"self-harm\":0.015232,\"self-harm/intent\":0.017179,\"self-harm/instructions\":0.01807,\"sexual\":0.035671,\"sexual/minors\":0.094207,\"violence\":0.665897,\"violence/graphic\":0.198346,\"illicit\":0.732167,\"illicit/violent\":0.780693}}]}",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 30,
"completion_tokens": 177,
"total_tokens": 207,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}
```
```json Responses API theme={null}
{
"id": "6b644bea-ed4a-43e6-b2ed-6a462c79c4e0",
"object": "response",
"created_at": 1786030511,
"status": "completed",
"completed_at": 1786030511,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "zlm-v1-moderation-edge",
"output": [
{
"type": "message",
"id": "6b644bea-ed4a-43e6-b2ed-6a462c79c4e0",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "{\"model\":\"zlm-v1-moderation-edge\",\"results\":[{\"flagged\":true,\"unsafe_score\":1,\"categories\":{\"hate\":false,\"hate/threatening\":false,\"harassment\":true,\"harassment/threatening\":true,\"self-harm\":false,\"self-harm/intent\":false,\"self-harm/instructions\":false,\"sexual\":false,\"sexual/minors\":false,\"violence\":true,\"violence/graphic\":false,\"illicit\":true,\"illicit/violent\":true},\"category_scores\":{\"hate\":0.21574,\"hate/threatening\":0.168273,\"harassment\":0.82545,\"harassment/threatening\":0.957703,\"self-harm\":0.015232,\"self-harm/intent\":0.017179,\"self-harm/instructions\":0.01807,\"sexual\":0.035671,\"sexual/minors\":0.094207,\"violence\":0.665897,\"violence/graphic\":0.198346,\"illicit\":0.732167,\"illicit/violent\":0.780693}}]}",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1,
"truncation": "auto",
"usage": {
"input_tokens": 30,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 177,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 207
},
"user": null,
"metadata": {}
}
```
JSON-parse that string to get the moderation result — `flagged`, `unsafe_score`, and the 13 `categories` with their `category_scores`:
```json Parsed moderation result theme={null}
{
"model": "zlm-v1-moderation-edge",
"results": [
{
"flagged": true,
"unsafe_score": 1,
"categories": {
"hate": false,
"hate/threatening": false,
"harassment": true,
"harassment/threatening": true,
"self-harm": false,
"self-harm/intent": false,
"self-harm/instructions": false,
"sexual": false,
"sexual/minors": false,
"violence": true,
"violence/graphic": false,
"illicit": true,
"illicit/violent": true
},
"category_scores": {
"hate": 0.21574,
"hate/threatening": 0.168273,
"harassment": 0.82545,
"harassment/threatening": 0.957703,
"self-harm": 0.015232,
"self-harm/intent": 0.017179,
"self-harm/instructions": 0.01807,
"sexual": 0.035671,
"sexual/minors": 0.094207,
"violence": 0.665897,
"violence/graphic": 0.198346,
"illicit": 0.732167,
"illicit/violent": 0.780693
}
}
]
}
```