Perplexity
Sonar Pro Search
Structured outputReasoningImage input
- Context
- 200K
- Listed
- 11mo ago
- Input / 1M tokens
- $3.00
- Output / 1M tokens
- $15.00
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Perplexity
- Model family
- Sonar
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Listed on OpenRouter
- October 30, 2025
- Model ID
perplexity/sonar-pro-search- Openness
- Closed
- License
- —
- Input modalities
- text, image
- Output modalities
- text
- Modality
- text+image->text
- Tokenizer
- Other
- Max output tokens
- 8K
- Hugging Face
- —
- Source freshness
- Endpoints synced Oct 15, 2026, 2:18 PM UTC
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| perplexity | 200K | $3.00 | $15.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter