Privacy Filter

Confidential TEE

openai/privacy-filter

PII detection (token classification) — returns spans for emails, phones, addresses, names, account numbers, secrets. NEAR AI runs this model in a TEE; prompts are not anonymized by the model itself, the cloud-api wraps it to do redaction.

Input / 1M tokens: $0.01
Output / 1M tokens: $0
Cache read / 1M tokens: —
Context window: 0K tokens

Privacy & execution

This model supports confidential inference inside a hardware-isolated Trusted Execution Environment (TEE), protecting data while it is processed. HTTPS protects data in transit; client-to-model end-to-end encryption depends on the model and integration.

Attestation provides cryptographic evidence of the execution environment’s identity and configuration. Where response signatures are available, you can also verify the integrity of the request and response.

Verification documentation

Make your first request

Call /v1/privacy/classify over HTTPS.

Get an API key and replace the API key placeholder below.

curl https://cloud-api.near.ai/v1/privacy/classify \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR-NEAR-AI-CLOUD-API-KEY>" \
  -d '{
  "model": "openai/privacy-filter",
  "input": "My name is John Smith and my email is john@example.com"
}'

Use the API

Use the dedicated endpoint for this model’s modality.

Use /v1/privacy/classify to detect PII spans or /v1/privacy/redact to replace them inline.

fetch("https://cloud-api.near.ai/v1/privacy/classify", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR-NEAR-AI-CLOUD-API-KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "openai/privacy-filter",
    "input": "My name is John Smith and my email is john@example.com"
  })
})