---
title: "Perplexity models: release history and timeline"
description: "Perplexity is a San Francisco company that builds an AI-powered answer engine, the Comet browser and Perplexity Computer, and post-trains its own Sonar and pplx-embed models."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/perplexity"
markdown_url: "https://theaiengineering.com/releases/perplexity.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-11-12"
citation: "The AI Engineering Editors. \"Perplexity models: release history and timeline.\" The AI Engineering, updated Nov 12, 2026. https://theaiengineering.com/releases/perplexity"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# Perplexity models: release history and timeline

Perplexity is a San Francisco company that builds an AI-powered answer engine, the Comet browser and Perplexity Computer, and post-trains its own Sonar and pplx-embed models.

- Headquarters: San Francisco, United States
- Founded: 2022
- Website: https://www.perplexity.ai

10 releases from 1 lab, 7 with open weights. Dates are the labs' official announcement dates.

## November 2026

### pplx-decider-v1.3 and pplx-decider-flash-v1.3

Perplexity's v1.3 decision models return a probability distribution over predefined answers to yes or no, multiple-choice, and ordered score questions in one forward pass. Decider v1.3 is fine-tuned from Qwen3.8-27B, and Decider Flash v1.3 is distilled from it onto Qwen3.5-4B.

- Date: 2026-11-12
- Lab: Perplexity
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → score
- Parameters: 27B and 4B
- License: Apache-2.0
- Available at launch: API, Open weights
- Permalink: https://theaiengineering.com/releases/2026/11#pplx-decider-v1-3

Highlights:

- Added Locate, which extracts exact text spans from the input with character offsets for entity recognition, PII detection, and extractive QA
- Perplexity reported 91.6% mean accuracy across 63 classification tasks for Decider v1.3, 6.54 points above its production classifiers
- Accepts images alongside text, as earlier Decider versions did
- Weights released on Hugging Face under Apache 2.0, with access through OpenRouter and the Perplexity Decisions API at launch

Source: [Perplexity Decider v1.3: Training, eval, and use cases](https://www.perplexity.ai/hub/blog/perplexity-decider)

## October 2026

### pplx-embed-v2-late-0.6b and pplx-embed-v2-late-9b

A family of late-interaction (ColBERT-style) embedding models in 0.6B and 9B sizes that output 128-dimensional vectors per token for text and image retrieval, including rendered PDF pages, in a shared embedding space.

- Date: 2026-10-07
- Lab: Perplexity
- Type: Embedding
- Weights: Open weights
- Modalities: text, image → embedding
- Parameters: 0.6b: 594M total; 9b: 7.4B active
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/10#pplx-embed-v2-late

Highlights:

- Scores query-document pairs with MaxSim over 128-dimensional token embeddings
- The 0.6B model can query an index built with the 9B model through the shared embedding space
- Built on Qwen3.5 with bidirectional attention; the 0.6B model is pruned from Qwen3.5-0.8B
- Weights on Hugging Face under the MIT license

Source: [Multimodal embeddings beyond a single vector](https://www.perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector)

## September 2026

### pplx-embed-v2-context-9b-preview

A preview contextual embedding model that embeds document chunks with their surrounding context, trained by distilling chunk relevance from Perplexity's context compression model to retrieve supporting context as well as answer chunks.

- Date: 2026-09-30
- Lab: Perplexity
- Type: Embedding
- Weights: Open weights
- Modalities: text → embedding
- Parameters: 9B
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/09#pplx-embed-v2-context

Highlights:

- Returns one INT8 embedding per chunk, with 1024- or 2048-dimensional (MRL) vectors
- Non-preview pplx-embed-v2-context-0.6b and -9b (text and image) followed on Hugging Face in October 2026
- Weights on Hugging Face under the MIT license

Source: [Contextual embedding beyond the gold passage](https://www.perplexity.ai/hub/blog/contextual-embedding-beyond-the-gold-passage)

### PII-Tracer

A compact 0.6B model for detecting personally identifiable information in long, multilingual conversations, released with the PII-TRACE benchmark and built for the local privacy gate in Perplexity Computer's hybrid compute on Mac.

- Date: 2026-09-01
- Lab: Perplexity
- Type: Small model
- Weights: Open weights
- Modalities: text → text
- Parameters: 0.6B
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/09#pii-tracer

Highlights:

- Bidirectional Qwen3 encoder initialized from pplx-embed-v1-0.6b, with token-tagging and sensitivity heads
- Tags 9 PII categories, including names, account numbers, addresses, emails and secrets
- Released with PII-TRACE, a 13-language benchmark for PII detection across conversations
- Weights on Hugging Face under the MIT license, plus GGUF and MLX builds

Source: [PII-TRACE: Detecting Personal Data Before It Leaves a Device](https://www.perplexity.ai/hub/blog/pii-trace-detecting-personal-data-before-it-leaves-the-device)

## February 2026

### pplx-embed-v1 and pplx-embed-context-v1

Two text embedding model families, pplx-embed-v1 for standard dense retrieval and pplx-embed-context-v1 for document-aware chunk embeddings, each in 0.6B and 4B sizes and built by diffusion continued pretraining of Qwen3.

- Date: 2026-02-26
- Lab: Perplexity
- Type: Embedding
- Weights: Open weights
- Modalities: text → embedding
- Parameters: 0.6B and 4B
- License: MIT
- Available at launch: API, Open weights
- Permalink: https://theaiengineering.com/releases/2026/02#pplx-embed-v1

Highlights:

- 32K-token context, native INT8 and binary embeddings, Matryoshka dimensions, no instruction prefixes
- API model IDs pplx-embed-v1-0.6b, pplx-embed-v1-4b, pplx-embed-context-v1-0.6b and pplx-embed-context-v1-4b
- Perplexity's Embeddings API became available the same month (February 2026)
- Weights on Hugging Face under the MIT license

Source: [pplx-embed: State-of-the-Art Embedding Models for Web-Scale Retrieval](https://www.perplexity.ai/hub/blog/pplx-embed-state-of-the-art-embedding-models-for-web-scale-retrieval)

## December 2025

### BrowseSafe

An open prompt-injection detection model fine-tuned from Qwen3-30B-A3B that reads a web page's HTML and answers whether it contains malicious instructions aimed at a browser agent, released with the BrowseSafe-Bench benchmark.

- Date: 2025-12-02
- Lab: Perplexity
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Context window: 16,384 tokens
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#browsesafe

Highlights:

- Outputs a single yes or no token for each page
- Context length up to 16,384 tokens per the model card
- BrowseSafe-Bench spans 11 attack types and 9 injection strategies
- Built for Perplexity's Comet browser; weights on Hugging Face under the MIT license

Source: [Building Safer AI Browsers with BrowseSafe](https://www.perplexity.ai/hub/blog/building-safer-ai-browsers-with-browsesafe)

## February 2025

### R1 1776

A version of DeepSeek-R1 that Perplexity post-trained on about 40,000 multilingual prompts covering topics censored by the Chinese Communist Party, aiming for factual answers while keeping R1's reasoning ability.

- Date: 2025-02-18
- Lab: Perplexity
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- License: MIT
- Available at launch: API, Open weights
- Permalink: https://theaiengineering.com/releases/2025/02#r1-1776

Highlights:

- Weights released on Hugging Face under the MIT license
- Also offered through Perplexity's Sonar API at launch
- Post-trained with an adapted version of NVIDIA's NeMo 2.0 framework
- Removed from the Perplexity API on August 1, 2025, per the API changelog

Source: [Open-sourcing R1 1776](https://web.archive.org/web/20250219025612/https://www.perplexity.ai/hub/blog/open-sourcing-r1-1776)

### Sonar (built on Llama 3.3 70B)

An updated version of Perplexity's in-house Sonar model, built on Llama 3.3 70B and further trained for answer factuality and readability in Perplexity's default search mode, served on Cerebras inference infrastructure.

- Date: 2025-02-11
- Lab: Perplexity
- Type: LLM
- Weights: Proprietary
- Modalities: text → text
- Parameters: 70B (Llama 3.3 70B base)
- Available at launch: API, Consumer app
- Permalink: https://theaiengineering.com/releases/2025/02#perplexity-sonar-2025-02

Highlights:

- Available to Perplexity Pro users, who can set it as their default model
- Perplexity reports about 1,200 tokens per second on Cerebras infrastructure
- Also offered via the Sonar API, which did not yet run on Cerebras at launch

Source: [Meet New Sonar: A Blazing Fast Model Optimized for Perplexity Search](https://www.perplexity.ai/hub/blog/meet-new-sonar)

## January 2025

### Sonar and Sonar Pro (API)

Perplexity's Sonar API models with built-in real-time web search and citations: Sonar for fast, lightweight answers and Sonar Pro for multi-step queries with more citations and a larger context window.

- Date: 2025-01-21
- Lab: Perplexity
- Type: LLM
- Weights: Proprietary
- Modalities: text → text
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2025/01#perplexity-sonar-pro

Highlights:

- API model IDs sonar and sonar-pro; Sonar Pro generally available to all developers at launch
- Model docs listed 127k context for sonar and 200k for sonar-pro, with an 8k output cap on sonar-pro
- Replaced the llama-3.1-sonar online models, which were retired on February 22, 2025
- JSON mode and search domain filters opened to select usage tiers

Source: [Introducing the Sonar Pro API by Perplexity](https://www.perplexity.ai/hub/blog/introducing-the-sonar-pro-api)

## November 2023

### pplx-7b-online and pplx-70b-online

Two online LLMs fine-tuned from Mistral 7B and Llama 2 70B to answer with snippets from Perplexity's own search index, giving API developers responses grounded in current web information.

- Date: 2023-11-29
- Lab: Perplexity
- Type: LLM
- Weights: Proprietary
- Modalities: text → text
- Parameters: pplx-7b-online: 7B (Mistral 7B base); pplx-70b-online: 70B (Llama 2 70B base)
- Available at launch: API, Consumer app
- Permalink: https://theaiengineering.com/releases/2023/11#pplx-7b-70b-online

Highlights:

- Available through pplx-api, which moved from beta to general release
- Also accessible in Perplexity Labs, the company's LLM playground
- Offline pplx-7b-chat and pplx-70b-chat models left alpha in the same release

Source: [Introducing PPLX Online LLMs](https://www.perplexity.ai/hub/blog/introducing-pplx-online-llms)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "Perplexity models: release history and timeline." The AI Engineering, updated Nov 12, 2026. https://theaiengineering.com/releases/perplexity

HTML link:

```html
<a href="https://theaiengineering.com/releases/perplexity">Perplexity models: release history and timeline</a> (The AI Engineering)
```

- Title: Perplexity models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-11-12
- URL: https://theaiengineering.com/releases/perplexity
- Markdown: https://theaiengineering.com/releases/perplexity.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
