Fast web-grounded Sonar for current answers, citations, and lightweight retrieval
Sonar by perplexity is offered by 11 providers on this page. Its official list price is $1.00 per 1M tokens. The lowest paid channel is Perplexity Agent at $0.25 / $2.50 per 1M, about 4.0× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 7.7 on the Intelligence Index. Against its lowest blended price of $0.813 per 1M, that is roughly 9 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 127,000 to 130,000, so the usable window depends on the provider you pick. Accepted input modalities are Text and Image. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-09-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Perplexity Agent | Gateway | $0.25 | $2.50 | $0.063 | — | 128,000 | 8,192 | |
| Vercel AI Gateway | Cloud | $0.25 | $2.50 | — | $0.063 | 127,000 ⚠ | 8,000 | |
| DevPass (LLM Gateway) | Gateway | $0.25 | $2.50 | — | $0.25 | 130,000 ⚠ | 4,096 | |
| LLM Gateway | Gateway | $0.25 | $2.50 | — | $0.25 | 130,000 ⚠ | 4,096 | |
| OpenRouter | Gateway | $1.00 | $1.00 | — | — | 127,072 ⚠ | 114,364 | |
| PerplexityOfficial | First-party | $1.00 | $1.00 | — | — | 128,000 | 4,096 | |
| Opper | Gateway | $1.00 | $1.00 | — | — | 128,000 | 4,096 | |
| Eden AI | Gateway | $1.00 | $1.00 | — | — | 127,072 ⚠ | 4,096 | |
| SAP AI Core | Cloud | $1.00 | $1.00 | — | — | 128,000 | 4,096 | |
| Kilo Gateway | Gateway | $1.00 | $1.00 | — | — | 127,072 ⚠ | 114,364 | |
| Helicone | Gateway | $1.00 | $1.00 | — | — | 127,000 ⚠ | 4,096 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SciCode | — | 22.9 | percent correct | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.