Perplexity models

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.

San Francisco, United StatesFounded 2022perplexity.ai

Releases
10
Open weights
7
Latest
Nov 12, 2026

November 2026

1 release
  1. MultimodalOpen weights

    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.

    Modalities
    text, image → score
    Parameters
    27B and 4B
    License
    Apache-2.0
    At launch
    API, Open weights
    • 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

October 2026

1 release
  1. EmbeddingOpen weights

    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.

    Modalities
    text, image → embedding
    Parameters
    0.6b: 594M total; 9b: 7.4B active
    License
    MIT
    At launch
    Open weights
    • 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

September 2026

2 releases
  1. EmbeddingOpen weights

    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.

    Modalities
    text → embedding
    Parameters
    9B
    License
    MIT
    At launch
    Open weights
    • 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
  2. Small modelOpen weights

    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.

    Modalities
    text → text
    Parameters
    0.6B
    License
    MIT
    At launch
    Open weights
    • 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

February 2026

1 release
  1. EmbeddingOpen weights

    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.

    Modalities
    text → embedding
    Parameters
    0.6B and 4B
    License
    MIT
    At launch
    API, Open weights
    • 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

December 2025

1 release
  1. LLMOpen weights

    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.

    Modalities
    text → text
    Context
    16K context
    License
    MIT
    At launch
    Open weights
    • 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

February 2025

2 releases
  1. ReasoningOpen weights

    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.

    Modalities
    text → text
    License
    MIT
    At launch
    API, Open weights
    • 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
  2. LLMProprietary

    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.

    Modalities
    text → text
    Parameters
    70B (Llama 3.3 70B base)
    At launch
    API, Consumer app
    • 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

January 2025

1 release
  1. LLMProprietary

    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.

    Modalities
    text → text
    At launch
    API
    • 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

November 2023

1 release
  1. LLMProprietary

    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.

    Modalities
    text → text
    Parameters
    pplx-7b-online: 7B (Mistral 7B base); pplx-70b-online: 70B (Llama 2 70B base)
    At launch
    API, Consumer app
    • 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

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 " | ".

Citation

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

HTML link

<a href="https://theaiengineering.com/releases/perplexity">Perplexity models: release history and timeline</a> (The AI Engineering)
Full dataset
1,167 releases from 55 labs
Coverage
to
Updated
License
CC BY 4.0
Publisher
The AI Engineering

Other labs