PerplexitySonar Reasoning Pro
Sonar Reasoning Pro is a Perplexity proprietary reasoning model, released 28 Jan 2025. It is not yet ranked: 1 independent result so far, and the index needs at least five across two categories. At $3.50 per million tokens blended it is among the most expensive ranked models. Output speed of 19 tokens per second puts it in the slowest quarter, with a first token in 23.9 s. Last measured 28 Jan 2025.stale: no new result in six months
- Blended price
- $3.50/M
- $2.00 in · $8.00 out
- Output speed
- 19 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 24 s
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 28 Jan 2025
- Composite43
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Composite
| Benchmark | thinking | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 11.8#343 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Perplexity | 18 tok/s | 9.65 s | $2.00 | $8.00 | 128k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0032 | – | 39.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.029 | – | 55.5 s |
| Code edit | 6,000 / 1,500 | $0.024 | – | 1.7 min |
| Agentic coding session | 60,000 / 4,000 | $0.152 | – | 3.9 min |
| Structured extraction | 2,000 / 200 | $0.0056 | – | 34.4 s |
See also
Questions people ask
- Why does Sonar Reasoning Pro have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 25 Oct 2026 Sonar Reasoning Pro has 1 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does Sonar Reasoning Pro cost per 1M tokens?
- As of 25 Oct 2026, Sonar Reasoning Pro costs $2.00 per 1M input tokens and $8.00 per 1M output tokens, $3.50 blended (three input tokens per output token).
- When was Sonar Reasoning Pro released?
- Perplexity released Sonar Reasoning Pro on 28 Jan 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Sonar Reasoning Pro: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/sonar-reasoning-pro.