5models tracked · ranked by intelligence, speed & price
its fastest is Sonar Pro at 93 tokens/sec, and its cheapest is Sonar at $1.00 per million input tokens. All 5 Perplexity models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| sonar-pro-search ReasoningJSONVision | — | 32 | 3.8s | $3.00 | 200K |
| sonar-reasoning-pro ReasoningVision | — | 40 | 15.9s | $2.00 | 128K |
| sonar-pro Vision | — | 93 | 1.9s | $3.00 | 200K |
| sonar-deep-research Reasoning | — | 36 | 40.2s | $2.00 | 128K |
| sonar Vision | — | 72 | 2.0s | $1.00 | 127K |