Loading activity…
@perplexitydevs
Official @perplexity_ai developer account for real-time API updates.
AI
Perplexity says text and vision scores improved, with inference up to 5x faster.
AI
A post also claims Perplexity Decider has the lowest cost.
Technology
Perplexity said it released pplx-decider-v1.1-27b, which it described as an updated open-weights multimodal decision model that scores highest on Hugging Face’s new Decision Index 0.3 benchmark and costs $0.02 per million input tokens, half as much as v1.
AI
Perplexity says its new pplx-decider-v1.1-27b model costs $0.02 per million input tokens, half the price of v1. OpenRouter later said the model was also available there with text, JSON, or image inputs and free output.
AI
The recipient says much of their work depends on agents running more capable code environments safely and reliably.
AI
Perplexity introduced a Decisions API built around pplx-decider-v1-27b, a multimodal model that returns probabilities over fixed answers instead of text, with weights available on Hugging Face.
AI
Perplexity says developers can configure agents in the API Portal using Profiles, Skills and managed connectors, then reuse them across applications and workflows.
XAI
Perplexity's guide describes how to assemble a source-backed dependency migration packet for a coding agent to inspect before it edits code.
AI
Stripe product lead Jeff Weinstein retweeted the announcement from Perplexity developers.
AI
Retweet by Perplexity CEO Aravind Srinivas of announcement from @perplexitydevs.
AI
Open 30B MoE model with 3B active parameters targets always-on agents.
