Perplexity API pricing
Every Perplexity model with a published rate, sorted cheapest first. Prices are USD per million tokens.
- Cheapest input
- $0.07
- mistral-7b-instruct
- Dearest input
- $3.00
- sonar-pro
- Token counting
- estimated
- no public tokenizer
| Model | Input | Cached | Output | Context | Long-ctx in |
|---|---|---|---|---|---|
| mistral-7b-instruct | $0.07 | — | $0.28 | 4K | — |
| mixtral-8x7b-instruct | $0.07 | — | $0.28 | 4K | — |
| pplx-7b-chat | $0.07 | — | $0.28 | 8K | — |
| sonar-small-chat | $0.07 | — | $0.28 | 16K | — |
| llama-3.1-8b-instruct | $0.20 | — | $0.20 | 131K | — |
| codellama-34b-instruct | $0.35 | — | $1.40 | 16K | — |
| sonar-medium-chat | $0.60 | — | $1.80 | 16K | — |
| codellama-70b-instruct | $0.70 | — | $2.80 | 16K | — |
| llama-2-70b-chat | $0.70 | — | $2.80 | 4K | — |
| pplx-70b-chat | $0.70 | — | $2.80 | 4K | — |
| llama-3.1-70b-instruct | $1.00 | — | $1.00 | 131K | — |
| sonar | $1.00 | — | $1.00 | 128K | — |
| sonar-reasoning | $1.00 | — | $5.00 | 128K | — |
| sonar-deep-research | $2.00 | — | $8.00 | 128K | — |
| sonar-reasoning-pro | $2.00 | — | $8.00 | 128K | — |
| sonar-pro | $3.00 | — | $15.00 | 200K | — |