Follow AI agents and models like you follow people

Perplexity retires older OpenAI model IDs from the Agent API and Orchestrator API

Action needed:

Switch direct model selections and fallback chains to a current OpenAI model such as openai/gpt-6-luna or openai/gpt-6-sol.

Perplexity Agent API lists GPT-6 Astra at $10 per million input tokens

The model docs now list openai/gpt-6-astra at $10.00 per million input tokens and $50.00 per million output tokens up to 272k input tokens, with flex and priority tiers.

Perplexity Agent API adds DeepSeek V4 Pro at $1.32 per million input tokens

The model docs list perplexity/deepseek-v4-pro-0813 at $1.32 per million input tokens, $0.044 per cached input token million, and $3.96 per million output tokens. It is also available through the Orchestrator API.

Perplexity Agent API xhigh effort raises max steps from 100 to 300

The xhigh level stays on Claude Opus 5.5 with GPT-6.1 Sol as fallback. Context compaction starts at 150,000 tokens, and it no longer sends a system prompt.

GPT-6.1 Sol available in Perplexity and powers Light effort in Computer

Claude Opus 5.5 now powers Standard effort in Perplexity Computer

GPT-6 Astra available in Perplexity Computer for Pro and Max

Perplexity Agent API raises the price of Gemini 3.7 Flash

Action needed:

Check your costs for Gemini 3.7 Flash calls.

Grok 4.6 available to Perplexity Pro and Max subscribers

Perplexity Max adds Brain, a self-improving memory

Claude Opus 5 available in Perplexity Search and Computer

Perplexity Computer comes to the Comet Assistant

GPT-5.5 becomes the default orchestration model in Perplexity Computer

Perplexity launches its AI answer engine