Perspective API alternative: migrate to Paxmod before December 31, 2026

curl, before (Perspective)

curl -X POST \
  "https://commentanalyzer.googleapis.com/v1alpha1/comments:analyze?key=$PERSPECTIVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "comment": { "text": "you are trash, uninstall" },
    "languages": ["en"],
    "requestedAttributes": { "TOXICITY": {}, "INSULT": {}, "THREAT": {} }
  }'

curl, after (Paxmod)

curl -X POST "https://www.paxmod.com/api/v1/text" \
  -H "Authorization: Bearer $PAXMOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "you are trash, uninstall",
    "user_id": "player_123",
    "context_id": "lobby_7"
  }'

Node, before (Perspective)

const res = await fetch(
  `https://commentanalyzer.googleapis.com/v1alpha1/comments:analyze?key=${process.env.PERSPECTIVE_API_KEY}`,
  {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({
      comment: { text },
      languages: ["en"],
      requestedAttributes: { TOXICITY: {} },
    }),
  }
);
const data = await res.json();
const isToxic = data.attributeScores.TOXICITY.summaryScore.value > 0.8;

Node, after (Paxmod)

const res = await fetch("https://www.paxmod.com/api/v1/text", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    Authorization: `Bearer ${process.env.PAXMOD_API_KEY}`,
  },
  body: JSON.stringify({ message: text, user_id: userId, context_id: channelId }),
});
const data = await res.json();
if (data.status === "error") throw new Error(data.error.code);

const isToxic = data.result === "flagged";
const harassment = data.content_moderation.categories["Harassment"]?.score ?? 0;

Python, before (Perspective)

import os, requests

r = requests.post(
    "https://commentanalyzer.googleapis.com/v1alpha1/comments:analyze",
    params={"key": os.environ["PERSPECTIVE_API_KEY"]},
    json={
        "comment": {"text": text},
        "languages": ["en"],
        "requestedAttributes": {"TOXICITY": {}},
    },
    timeout=5,
)
is_toxic = r.json()["attributeScores"]["TOXICITY"]["summaryScore"]["value"] > 0.8

Python, after (Paxmod)

import os, requests

r = requests.post(
    "https://www.paxmod.com/api/v1/text",
    headers={"Authorization": f"Bearer {os.environ['PAXMOD_API_KEY']}"},
    json={"message": text, "user_id": user_id, "context_id": channel_id},
    timeout=5,
)
data = r.json()
is_toxic = data.get("result") == "flagged"
harassment = data.get("content_moderation", {}).get("categories", {}).get("Harassment", {}).get("score", 0)

Is Perspective API shutting down?

Yes. Google's Jigsaw team is sunsetting Perspective API. It stays live until December 31, 2026 and stops working after that. Usage and quota requests closed in February 2026, and Google is not offering migration support.

Can I replace Perspective API without changing my request format?

No. Paxmod uses its own request and response format, so you change the endpoint, the auth header and the fields you read. For most integrations that is one function. This page has the full field mapping and before and after code in curl, Node and Python.

How do Perspective attributes map to Paxmod categories?

TOXICITY maps to Harassment, Hate and Discrimination and Profanities. SEVERE_TOXICITY maps to Threatening, Violence and Hate and Discrimination. IDENTITY_ATTACK maps to Hate and Discrimination, INSULT to Harassment, THREAT to Threatening and Violence, PROFANITY to Profanities and SEXUALLY_EXPLICIT to Sexual. FLIRTATION has no fixed category, so write it as an Advanced mode policy.

Can I reuse my Perspective thresholds?

Not directly. Paxmod scores come from different models, so a 0.8 in Perspective is not a 0.8 in Paxmod. Run both APIs on the same traffic while Perspective is still live, then set each Paxmod category threshold in the console. The default is 0.5.

How long does the migration take?

The code change is usually a single function: new URL, a Bearer header, a different field to read. Leave extra time to shadow-run both APIs and tune thresholds before December 31.

Does Paxmod work for game chat on Minecraft, Roblox and Unity?

Yes. Paxmod is built for Minecraft, Roblox, and Unity game chat. See the Minecraft, Roblox and Unity integration guides.

How much does Paxmod cost?

Plans start at $29/month with 50,000 message credits, and Studio is $149/month with 500,000. Every plan starts with a 14-day free trial with 10,000 messages and every feature.

What is the maximum message length?

5,000 characters per message. Perspective accepted up to 20 KB, so split longer comments or posts into parts and check each one.