PE

perplexity-upgrade-migration

Migrate your codebase between Perplexity model generations and handle parameter changes. Identify deprecated code effectively.

Install

mkdir -p .claude/skills/perplexity-upgrade-migration && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5356" && unzip -o skill.zip -d .claude/skills/perplexity-upgrade-migration && rm skill.zip

Installs to .claude/skills/perplexity-upgrade-migration

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Migrate between Perplexity model generations and API parameter changes.
71 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Detect deprecated Perplexity model names
  • Migrate legacy API base URLs to current endpoints
  • Update parameter configurations for current API specifications
  • Verify connection with new Sonar models
  • Create git branches for migration testing

How it works

The skill scans source files for deprecated model names and legacy base URLs, then applies a migration map to update them to current Sonar standards and API endpoints.

Inputs & outputs

You give it
Source code containing legacy Perplexity API patterns
You get back
Updated code with current model names, URLs, and parameters

When to use perplexity-upgrade-migration

  • Upgrading to new Sonar models
  • Identifying legacy API usage
  • Refactoring code after model deprecation
  • Updating Perplexity SDK versions

About this skill

Perplexity Upgrade & Migration

Current State

!npm list openai 2>/dev/null | grep openai || echo 'openai not installed' !pip show openai 2>/dev/null | grep Version || echo 'N/A'

Overview

Guide for migrating between Perplexity model generations and API changes. Perplexity has evolved from pplx-api with third-party models to the Sonar family with built-in web search.

Model Evolution

EraModelsStatus
Legacy (pre-2025)pplx-7b-online, pplx-70b-online, llama-3.1-sonar-*Deprecated
Current (2025)sonar, sonar-proActive
Extended (2025+)sonar-reasoning-pro, sonar-deep-researchActive

Instructions

Step 1: Identify Legacy Patterns to Update

set -euo pipefail
# Find deprecated model names in your codebase
grep -rn "pplx-7b\|pplx-70b\|llama.*sonar\|sonar-small\|sonar-medium\|sonar-huge" \
  --include="*.ts" --include="*.py" --include="*.js" --include="*.json" \
  . 2>/dev/null || echo "No legacy models found"

# Find old base URLs
grep -rn "api.perplexity.com\|pplx.readme.io" \
  --include="*.ts" --include="*.py" --include="*.js" \
  . 2>/dev/null || echo "No legacy URLs found"

Step 2: Model Name Migration Map

// Migration map: old model name -> new model name
const MODEL_MIGRATION: Record<string, string> = {
  // Legacy pplx-api models (fully deprecated)
  "pplx-7b-online": "sonar",
  "pplx-70b-online": "sonar-pro",
  "pplx-7b-chat": "sonar",
  "pplx-70b-chat": "sonar",

  // Llama-era Sonar models (deprecated)
  "llama-3.1-sonar-small-128k-online": "sonar",
  "llama-3.1-sonar-large-128k-online": "sonar-pro",
  "llama-3.1-sonar-huge-128k-online": "sonar-pro",
  "sonar-small-online": "sonar",
  "sonar-medium-online": "sonar-pro",

  // Current models (no migration needed)
  "sonar": "sonar",
  "sonar-pro": "sonar-pro",
  "sonar-reasoning-pro": "sonar-reasoning-pro",
  "sonar-deep-research": "sonar-deep-research",
};

function migrateModel(model: string): string {
  const migrated = MODEL_MIGRATION[model];
  if (!migrated) {
    console.warn(`Unknown Perplexity model: ${model}. Defaulting to sonar.`);
    return "sonar";
  }
  if (migrated !== model) {
    console.warn(`Perplexity model ${model} is deprecated. Using ${migrated}.`);
  }
  return migrated;
}

Step 3: URL Migration

// Old URLs -> New URL
const BASE_URL_MIGRATION: Record<string, string> = {
  "https://api.perplexity.com": "https://api.perplexity.ai",
  "https://pplx-api.perplexity.ai": "https://api.perplexity.ai",
};

// Current canonical base URL
const PERPLEXITY_BASE_URL = "https://api.perplexity.ai";

Step 4: Parameter Changes

// Parameters that changed between API versions
// OLD: return_citations: true
// NEW: Citations are always returned in the response object

// OLD: No search_recency_filter
// NEW: search_recency_filter: "hour" | "day" | "week" | "month"

// OLD: No search_domain_filter
// NEW: search_domain_filter: string[] (max 20, prefix with - to exclude)

// OLD: No return_related_questions
// NEW: return_related_questions: true (closed beta)

// OLD: No return_images
// NEW: return_images: true (Tier-2+ only)

// OLD: No search_after_date_filter / search_before_date_filter
// NEW: search_after_date_filter: "3/1/2025" (mm/dd/yyyy format)

Step 5: Upgrade OpenAI SDK

set -euo pipefail
# Create upgrade branch
git checkout -b upgrade/perplexity-sonar-migration

# Upgrade OpenAI SDK to latest
npm install openai@latest
# or
pip install --upgrade openai

# Run tests
npm test

# Verify connection with new models
node -e "
const OpenAI = require('openai');
const c = new OpenAI({apiKey: process.env.PERPLEXITY_API_KEY, baseURL: 'https://api.perplexity.ai'});
c.chat.completions.create({model:'sonar', messages:[{role:'user',content:'test'}], max_tokens:5})
  .then(r => console.log('OK:', r.model))
  .catch(e => console.error('FAIL:', e.message));
"

Rollback

set -euo pipefail
# If the upgrade breaks things, revert
git checkout main -- package.json package-lock.json
npm install

Error Handling

IssueCauseSolution
Invalid model errorUsing deprecated model nameApply model migration map
Connection refusedWrong base URLUse https://api.perplexity.ai
Missing citationsExpecting old response formatCitations are in response.citations array
Parameter rejectedUsing old parameter namesCheck current parameter list

Output

  • Updated model names to current Sonar family
  • Corrected base URL to api.perplexity.ai
  • Updated parameters to current API spec
  • Passing test suite

Resources

Next Steps

For CI integration during upgrades, see perplexity-ci-integration.

When not to use it

  • When using current Sonar models that require no migration
  • When the project does not use the Perplexity API

Prerequisites

Perplexity API keyGitnpm or pip

Limitations

  • Requires manual verification of test results after automated updates
  • Limited to patterns defined in the migration map

How it compares

This automates the identification and replacement of deprecated patterns across a codebase, whereas manual migration requires searching and updating each instance individually.

Compared to similar skills

perplexity-upgrade-migration side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
perplexity-upgrade-migration (this skill)127dReviewIntermediate
openrouter-hello-world727dCautionBeginner
telegram-dev28moReviewIntermediate
ast-grep-find37moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

Search skills

Search the agent skills registry