LLMPrice.io

Sonar API pricing

Published on-demand rates for Perplexity's perplexity/sonar, captured 2026-08-10 from public pricing data and committed to our archive. Context window 128k tokens; first observed in our archive 2025-02-17.

MeterUSD per 1M tokens
Input$1.00
Output$1.00
Cached inputno published cache-read rate; the whole input bills at the standard rate

Standard on-demand rates. Excludes batch endpoints and negotiated pricing; confirm on Perplexity's pricing page before committing.

What it costs on a real workload

The four frozen profiles the LLMPrice indices price, per 1M tokens processed, at the rates above. Where no cache-read rate is published, the whole input bills at the standard rate.

ProfileIn / out mixCached shareCost
Retrieval800k / 200k70%$1.00
Chat500k / 500k30%$1.00
Content200k / 800k20%$1.00
Agent900k / 100k85%$1.00

Profile definitions are frozen and published on the methodology page. Compare every model on these profiles →

Observed rate history

No repricing observed since this model entered our archive on 2025-02-17. When a rate moves, the change appears here and on the sitewide ticker.

Priced near this one

The models closest to Sonar on a retrieval workload, cheaper and more expensive alike. We publish no quality score, so this is what they cost and nothing more.

ModelProviderInputOutputvs Sonar
Grok 3 Mini FastxAI$0.600$4.003% more
Grok 4.3xAI$1.25$2.509% less
GPT 5.4 MiniOpenAI$0.750$4.5012% more
Mistral MediumMistral$0.400$2.0028% less

Compared on the retrieval profile: 800k input, 200k output, 70% of input cached where the model offers a cache rate.

Price your own prompt on it Estimate a whole project Plain rate card Perplexity's console →

No affiliate or referral arrangements: the console link carries no parameters and nothing on this page is paid placement. Sonar is a trademark of its owner; LLMPrice.io is independent and unaffiliated.