Pricing
| Model | Input Tokens (Per Million Tokens) | Output Tokens (Per Million Tokens) | Price per 1000 searches |
|---|---|---|---|
sonar-reasoning-pro | $2 | $8 | $5 |
sonar-reasoning | $1 | $5 | $5 |
sonar-pro | $3 | $15 | $5 |
sonar | $1 | $1 | $5 |
r1-1776 | $2 | $8 | - |
r1-1776 is an offline chat model that does not use our search subsystem
Detailed Pricing Breakdown for Sonar Reasoning Pro and Sonar Pro
Input Tokens
-
Input tokens are priced at $3/1M tokens
-
Input tokens comprise of Prompt tokens (user prompt) + Citation tokens (these are processed tokens from running searches)
Search Queries
-
To give detailed answers, both the Pro APIs also run multiple searches on top of the user prompt where necessary for more exhaustive information retrieval
-
Searches are priced at $5/1000 searches
-
A request that does 3 searches will cost $0.015 in this step.
Output Tokens
- Output tokens (Completion tokens) are priced at $15/1M tokens
Total Price
Your total price per request finally is a sum of the above 3 components
Sonar Reasoning and Sonar
Citation tokens are not considered as part of input tokens and each request does 1 search for Sonar Reasoning and Sonar.
Legacy Models
These models will be deprecated and will no longer be available to use after 2/22/2025
| Model | Input Tokens (Per Million Tokens) | Output Tokens (Per Million Tokens) | Price per 1000 requests |
|---|---|---|---|
llama-3.1-sonar-small-128k-online | $0.2 | $0.2 | $5 |
llama-3.1-sonar-large-128k-online | $1 | $1 | $5 |
llama-3.1-sonar-huge-128k-online | $5 | $5 | $5 |