Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
With CoreAI, you can start chatting with Perplexity: Sonar Deep Research instantly — no separate subscription needed. CoreAI lets you chat with Perplexity: Sonar Deep Research alongside 300+ other AI models from Perplexity and other providers like OpenAI, Anthropic, Google, Meta, and more.
Among the 392 chat models on CoreAI, Perplexity: Sonar Deep Research ranks #320 by context window — 128K tokens, roughly 96,000 words or 192 pages of text in a single conversation. On price, it is the #161 cheapest of 183 standard-tier models by input cost. It joined the catalog on 2025-03-07. It supports step-by-step reasoning (thinking mode).
Every model in this table is available on CoreAI — open the web app and run the same prompt through Perplexity: Sonar Deep Research and Perplexity: Sonar Reasoning Pro side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00600 on Perplexity: Sonar Deep Research's raw per-token rates; a heavy session with a 50K-token document costs about $0.140. On CoreAI you don't juggle these numbers — one subscription covers Perplexity: Sonar Deep Research and 300+ other models under a plan usage limit, with no API keys. See plans.
Perplexity: Sonar Deep Research handles 128K tokens of context — roughly 96,000 words, or about 192 pages of text in one conversation.
Perplexity: Sonar Deep Research's underlying rates are $2 per 1M input tokens and $8 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
No — Perplexity: Sonar Deep Research is text-only. If you need image understanding, its standard-tier peers with vision are listed in the comparison table above.
Yes. Perplexity: Sonar Deep Research can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.
Open the CoreAI web app or the iOS/Android app, pick Perplexity: Sonar Deep Research in the model selector, and chat — no API key, no per-token billing. One subscription covers Perplexity: Sonar Deep Research and 300+ other models.
The closest alternatives on CoreAI are Perplexity: Sonar Reasoning Pro, Deep Cogito: Cogito v2.1 671B, inclusionAI: Ling-2.6-flash — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with Perplexity: Sonar Deep Research and 300+ other AI models — all in one app.