Sonar Deep Research
Pricing & Specs

Perplexity · $2 input / $8 output per 1M tokens · 128K context window

No longer offered on OpenMark

$2
per 1M input tokens
$8
per 1M output tokens
128K
context window (tokens)

Sonar Deep Research is no longer offered on OpenMark (deprecated or superseded upstream).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 Deep Research API Pricing

TokensPrice
Input$2 / 1M tokens
Output$8 / 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): $0.0060
1K 1,000 runs of that task: $6.00
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Sonar Deep Research Specs

SpecValue
Context window128K tokens
Input modalitiestext
Output modalitiestext
Reasoning modelYes
Tool / function callingNo
JSON modeYes
StreamingYes
Prompt cachingNo

Capabilities

web search reasoning streaming structured outputs

Notes

⚠️ Request fee applies. Rate-limited; disabled in DMS by default.

FAQ

How much does Sonar Deep Research cost?

Sonar Deep Research costs $2 per 1M input tokens and $8 per 1M output tokens.

What is Sonar Deep Research's context window?

Sonar Deep Research has a 128K-token context window.

Can I test Sonar Deep Research on my own task?

Sonar Deep Research 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 Deep Research?

It's been superseded.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 →