Context
128K
Max output
8K
Serving providers
3
Cheapest input
$1.00 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisHeadline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| GPQA Diamond | 47% | default | — | |
| Humanity's Last Exam | 5% | default | — | |
| LiveCodeBenchArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 30% | — | — | |
| MMLU-ProFrozen Aug 18, 2026 | 69% | default | — | |
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 23% | — | — |
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.25 to $1.00 per 1M tokens across 3 providers, so the dearest route costs 300% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VercelVercel reseller quote | $0.25 | $2.50 | 1 | ||||||||||||||||
Standardperplexity/sonar
| |||||||||||||||||||
| OpenRouter | $1.00 | $1.00 | 1 | ||||||||||||||||
Standardperplexity/sonar
| |||||||||||||||||||
| PerplexityCheapest | $1.00 | $1.00 | 1 | ||||||||||||||||
Standardperplexity/sonar
| |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$250
estimated / month
Model IDs
copy the exact identifier for your platformperplexity/sonarperplexity/sonarperplexity/sonar
Frequently asked questions
Sonar pricing, context and availabilityHow much does Sonar cost?
Sonar costs $1.00 per 1M input tokens from Perplexity, and $1.00 per 1M output tokens from Perplexity. Across 3 serving providers, input prices range from $0.25 to $1.00 per 1M tokens.
What is the context window of Sonar?
Sonar accepts up to 128K tokens of context and can return up to 8K output tokens.
Which providers serve Sonar?
Sonar is available from 3 serving providers, each with its own pricing and model ID. Perplexity is currently the cheapest.
What can Sonar do?
Sonar supports web search.
Other Perplexity models
compare pricing across the Perplexity lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI