Perplexity

Sonar Reasoning

128K ctxText Reasoning

Released Jan 21, 2025 · 14B tokens this week · 1 provider

Overview

A reasoning-tuned search model that plans a query strategy, reads sources, then explains how it got there. Suited to research questions that need several hops across the web. Slower than plain Sonar but much better at synthesis.

reasoningacademiahealth

Providers

Reference data — not yet measured from live traffic

PROVIDERMAX OUTOUTPUT /MQUANT
PerplexityCheapest
128K8K$1.00$5.001,240ms4899.50%Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

Sonar Reasoning$4.00
GPT-5.2$10.94

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity/sonar-reasoning",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'