Vendor
Perplexity models
5 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
5
0 routable here
Median list price
$3.50
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Perplexity model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Sonar Pro Searchperplexity/sonar-pro-search | Oct 30, 2025 | 200K | $3.00 | $15.0 | - | reasoning |
| Sonar Reasoning Properplexity/sonar-reasoning-pro | Mar 7, 2025 | 128K | $2.00 | $8.00 | - | reasoning |
| Sonar Properplexity/sonar-pro | Mar 7, 2025 | 200K | $3.00 | $15.0 | - | |
| Sonar Deep Researchperplexity/sonar-deep-research | Mar 7, 2025 | 128K | $2.00 | $8.00 | - | reasoning |
| Sonarperplexity/sonar | Jan 27, 2025 | 127K | $1.00 | $1.00 | - |
Frequently asked
- What is the cheapest Perplexity model?
- Sonar at $1.00 per 1M input tokens and $1.00 per 1M output tokens (vendor list price).
- Which Perplexity model has the largest context window?
- Sonar Pro Search accepts 200K tokens of context.
- How do I route to Perplexity models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example perplexity/sonar-pro-search); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Perplexity with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Perplexity flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.