Mid-tier Anthropic model for everyday work, coding and document creation, with a 1 million token context window
pplx-decider-v1-27b
New· 4Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems
- United States
- San Francisco, Ca
- Artificial Intelligence Software
- Machine Learning
About pplx-decider-v1-27b
Perplexity published pplx-decider-v1-27b on Hugging Face on 1 October 2026 as an open-weight decision model. Rather than writing free text, it classifies input and chooses among the options supplied with a prompt, which is the job a routing or checking step needs. The model card tags it for text classification. Its use cases are the constrained questions that sit inside an agent system: deciding where a request should go, judging whether an output is acceptable, or gating an action before it runs.
Open weights under Apache 2.0
The weights are free to download under the Apache 2.0 license. Built by tuning the Qwen3.8-27B base model, it carries roughly 27 billion parameters and reads contexts of 262,144 tokens. No hosted price is stated, so use means running the weights, or a hosted copy, under the terms of that license.
Where it sits among other decision models
On eleven benchmarks, measured through its own API, Perplexity reports that the model scores higher overall than rival decision models. Those results are the company's own, and no third-party score was available to check. It arrives alongside other early-October decision models, among them the Clef family and Strands Decider 2B, which gives buyers several options to compare before choosing one.
TrustList summary
pplx-decider-v1-27b is an open-weight decision model that Perplexity posted to Hugging Face on 1 October 2026. Its licence is Apache 2.0. It builds on the Qwen3.8-27B base model through fine-tuning and is aimed at AI systems that need a constrained answer rather than free text.
What pplx-decider-v1-27b offers
- Option selection: classifies text and picks one of the options supplied with the prompt, instead of writing open-ended text.
- Routing and gating: for sending requests down the right path, checking outputs and controlling actions inside agent systems.
- Context: a context of 262,144 tokens.
- Benchmarks: Perplexity reports higher overall accuracy across eleven benchmarks, measured through its own API.
Who it works with
It fits teams building AI systems that route requests or check outputs. It joins several decision models released in early October, including the Clef models and Strands Decider 2B.
Key facts
- Published: 1 October 2026
- Licence: Apache 2.0
- Base model: Qwen3.8-27B, fine-tuned
- Context: 262,144 tokens
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
pplx-decider-v1-27b launches
Categories & features
- United States
- San Francisco, Ca
- Artificial Intelligence Software
- Machine Learning
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 10/5/2026
Request a demo or quote from pplx-decider-v1-27b
Reviews
Write the first review of pplx-decider-v1-27b
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about pplx-decider-v1-27b.
pplx-decider-v1-27b alternatives
Similar listings buyers compare against this one.
OpenAI's mid-tier GPT-6 model with a 1.05-million token context, image input and multi-agent support in beta
Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026
Open-weight agentic coding model from IQuestLab with a 524,288-token context, for teams that self-host
Google's frontier model, announced in September 2026 and released first to selected cyber defenders
Diffusion language model from Inception for enterprise teams building real-time voice agents, announced in September 2026
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Lower-cost sibling of Cohere's Embed 5 Pro, for high-volume multimodal embedding and indexing across 100+ languages
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- More United StatesBack to the ranked category
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.