NEAR AICloud
Sign inStart building
Privacy Filter icon
Privacy Filter
openai/privacy-filter
0K context|$0.01/M input tokens|— output|— cache read

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 / M tokens
$0.01
Output / M tokens
—
Cache read
—
Context
0K

Sample code and API for Privacy Filter

This model uses a dedicated classification endpoint, not chat completions. 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"
  })
})

Verify Privacy Filter

This model is hosted in a GPU TEE. TEE enables strong privacy with end-to-end encryption for data in transmission and in use. TEE protects the entire lifecycle of the model inference and gives you a proof of the execution. It allows you to verify that the given a model and an input, it produces a specific output both onchain and offchain.

Check out the docs for more details.

Get the attestation report.

curl 'https://cloud-api.near.ai/v1/attestation/report?model=openai/privacy-filter' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <NEAR_AI_CLOUD_API_KEY>'