PerplexityReasoning modelSonar Pro
Not yet ranked: too few independent results so far. Released 1 Jan 2024.
- Blended price
- $3.50/M
- $2.00 in · $8.00 out
- Output speed
- 51 tok/s
- First answer
- 3.10 s
- Context
- 128k
- Composite44
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| thinkingbest | – | – | 51 tok/s | 3.10 s | $0.0032 | Composite 44 |
| default | – | – | 51 tok/s | 3.10 s | $0.0057 | Composite 39 |
Benchmark results
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.
Reasoning
| Benchmark | thinking | default | Source |
|---|---|---|---|
| GPQA Diamond (AA)not in index | – | 57.8%#370 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | – | 6.5%#315 | Artificial Analysis |
Composite
| Benchmark | thinking | default | Source |
|---|---|---|---|
| AA Intelligence Index | 11.8#277 | 7.6#386 | 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 | 51 tok/s | 3.10 s | $3.00 | $15.00 | 200k | – |
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 | – | 9.0 s |
| Summarise a 30-page report | 12,000 / 600 | $0.029 | – | 14.9 s |
| Code edit | 6,000 / 1,500 | $0.024 | – | 32.5 s |
| Agentic coding session | 60,000 / 4,000 | $0.152 | – | 1.4 min |
| Structured extraction | 2,000 / 200 | $0.0056 | – | 7.0 s |
See also
Data as of 9 Sept 2026. Compare these configurations.