ShieldAI Content Moderation
Fast, AI-powered content moderation API. Detect hate speech, profanity, PII, spam, and more. BYOK for AI-enhanced analysis.
1 subscribers
11 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
ShieldAI Content Moderation endpoints
| Method | Endpoint | Description |
|---|---|---|
| Moderation | ||
| POST |
moderate_text_batch_v1_moderate_text_batch_post /v1/moderate/text/batch |
Moderate up to 100 text items in a single request. Pro and Enterprise plans only. |
| POST |
moderate_image_v1_moderate_image_post /v1/moderate/image |
Analyze images for inappropriate content. Currently in beta. |
| POST |
moderate_text_v1_moderate_text_post /v1/moderate/text |
Analyze text content for harmful material across multiple categories including hate speech, harassment, profanity, violence, spam, PII detection, and more. **Categories… |
| Account | ||
| POST |
register_v1_register_post /v1/register |
Register for a free account and receive your API key instantly. |
| API Keys | ||
| DELETE |
deactivate_key_v1_keys__key_id__delete /v1/keys/{key_id} |
|
| POST |
create_key_v1_keys__post /v1/keys/ |
|
| GET |
list_keys_v1_keys__get /v1/keys/ |
|
| Moderation Policies | ||
| POST |
create_policy_v1_policies__post /v1/policies/ |
Create a custom policy to tune moderation thresholds for your specific use case. **Example use cases:** - Gaming chat: Lower profanity threshold, higher violence threshold -… |
| GET |
list_policies_v1_policies__get /v1/policies/ |
|
| Usage & Analytics | ||
| GET |
get_usage_v1_usage__get /v1/usage/ |
|
| System | ||
| GET |
health_health_get /health |
|
ShieldAI Content Moderation pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | $1 / month | 100 / hour |
|
| PRO Recommended | $29 / month | — |
|
| ULTRA | $99 / month | — |
|
