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 — 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 →