Sonar Pro
Pricing & Specs

Perplexity · $3 input / $15 output per 1M tokens · 200K context window

$3
per 1M input tokens
$15
per 1M output tokens
200K
context window (tokens)

The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on Sonar Pro costs about $0.0105, roughly $10.50 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.

Sonar Pro API Pricing

TokensPrice
Input$3 / 1M tokens
Output$15 / 1M tokens

No cache pricing is published. Batch pricing is not documented.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0105
1K 1,000 runs of that task: $10.50
💡 Real cost depends on how verbose the model is on YOUR prompts. Benchmark to measure actual tokens, not estimates.

Sonar Pro Specs

SpecValue
Context window200K tokens
Input modalitiestext, image
Output modalitiestext
Latency (measured by OpenMark)~756ms median response
Reasoning modelNo
Tool / function callingNo
JSON modeYes
StreamingYes
Prompt cachingNo

Capabilities

web search citations streaming structured outputs images

Notes

⚠️ Request fee applies - Small benchmarks may cost more credits than token-only models.

FAQ

How much does Sonar Pro cost?

Sonar Pro costs $3 per 1M input tokens and $15 per 1M output tokens.

What is Sonar Pro's context window?

Sonar Pro has a 200K-token context window.

Can I test Sonar Pro on my own task?

Yes. OpenMark lets you benchmark Sonar Pro against 100+ models on your own task with real API calls, with no API keys needed, free tier available.

Is Sonar Pro the right model for YOUR task?

Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload: real API calls, real costs. Free tier available.

Benchmark Sonar Pro Free →

Get the monthly model change report

New models, API price changes, and retirements, straight from the registry that powers OpenMark. One email a month.