Sonar Reasoning
Pricing & Specs

Perplexity · $1 input / $5 output per 1M tokens · 128K context window

No longer offered on OpenMark

$1
per 1M input tokens
$5
per 1M output tokens
128K
context window (tokens)

Sonar Reasoning is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Sonar Reasoning API Pricing

TokensPrice
Input$1 / 1M tokens
Output$5 / 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): $0.0035
1K 1,000 runs of that task: $3.50
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Sonar Reasoning Specs

SpecValue
Context window128K tokens
Input modalitiestext, image
Output modalitiestext
Latency (measured by OpenMark)~8.1s median response
Reasoning modelYes
Tool / function callingNo
JSON modeYes
StreamingYes
Prompt cachingNo

Capabilities

reasoning web search streaming structured outputs

Notes

Use sonar-reasoning-pro instead. ⚠️ Request fee applies.

FAQ

How much does Sonar Reasoning cost?

Sonar Reasoning costs $1 per 1M input tokens and $5 per 1M output tokens.

What is Sonar Reasoning's context window?

Sonar Reasoning has a 128K-token context window.

Can I test Sonar Reasoning on my own task?

Sonar Reasoning is no longer offered on OpenMark, but you can benchmark its current alternatives from Perplexity and other providers on your own task — free tier available.

Still using Sonar Reasoning?

It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives — Free →