Perplexity API pricing (USD per 1M tokens)
Compare Perplexity models from the same validated snapshot as the full AI API pricing comparison. Prices are list estimates — confirm on your billing console.
Focused vendor table with the same normalization as the main pricing tracker—use it to shortlist SKUs, then open the full tool for filters and compare.
- List-price estimates — not invoices
- Confirm on vendor consoles
- Source: aggregated public catalog
Last updated · Snapshot timestamp unavailable for this build.
| Provider | Model id | Display name | Input cost / 1M | Cached input / 1M | Output cost / 1M | Context window | Max response | Modality | Link |
|---|---|---|---|---|---|---|---|---|---|
| No rows for this provider in the current snapshot yet. Open the full catalog table. | |||||||||
About AI API pricing units
Input vs output tokens: Providers typically bill prompts (input) and completions (output) separately. Cached or discounted input appears when the vendor publishes separate rates.
What “per 1M tokens” means: Token counts depend on tokenizer and language; treat comparisons as directional unless you meter your own prompts.