Perplexity: Sonar Deep Research API Pricing
Perplexity: Sonar Deep Research costs $2.00 per 1M input tokens and $8.00 per 1M output tokens. Context window: 128K. Prices verified 2026-10-21 · source
Alternatives to consider
Cheapest perplexity model — 71% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $2.00 | — |
| Output | $8.00 | — |
| Web search tool | $5/1k searches | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Higher effort = deeper thinking = more reasoning tokens billed as output.
What would Perplexity: Sonar Deep Research cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $48.00 |
| Coding agent | 5,000 | 8,000 / 2,000 | $160.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $360.00 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $96.00 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Perplexity: Sonar Deep Research
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...
Compare Perplexity: Sonar Deep Research with
- Deep Research vs OpenAI: GPT-5.6 Terra Pro
- Deep Research vs Anthropic: Claude Fable 5
- Deep Research vs Anthropic: Claude Opus 5
- Deep Research vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does Perplexity: Sonar Deep Research cost?
Perplexity: Sonar Deep Research costs $2.00 per 1M input tokens and $8.00 per 1M output tokens. Verified 2026-10-21 — provider source.
What is the context window?
128K tokens, with up to 115K output tokens per response. That's roughly 160 pages of text in a single request.
Does it support prompt caching?
Prompt-caching pricing is not published for this model via OpenRouter.
What's a cheaper alternative?
ScaleDown: Summarize saves about 99% on a typical workload with comparable quality.
Official resources
- Perplexity: Sonar Deep Research on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Shred your current bill — paste a CSV and see if switching saves money.