Skip to content
All models
PerplexityAvailable

Sonar

Sonar is a text model from Perplexity. It takes text and images as input and returns text. Its context window is 127,072 tokens. It costs 1.241177 credits per 1M input tokens, 1.241177 credits per 1M output tokens, and 0.006206 credits per request.

Try in ewpireperplexity/sonar

Opens in the ewpire workspace. Creating an account is free; runs are paid from your credits.

Sonar in plain words

It reads images as well as text. A context window of 127,072 tokens holds about 510,000 characters of English text, at 4 characters a token.

For example, a question of 2,000 tokens (about 8,000 characters) with an answer of 1,000 tokens (about 4,000 characters) costs 0.00993 credits, the fee per request included. The exact charge follows the usage the model reports for your request.

Details

Made by
Perplexity
Good at
Vision
Reads
Text, Images
Produces
Text
Context window
127,072 tokens

Price

Input, per 1M tokens
1.241177 credits
Output, per 1M tokens
1.241177 credits
Plus, per request
0.006206 credits

Charged per request from your credit balance. No subscription. See pricing

Use it through the API

Call it with the OpenAI SDK or plain HTTP: set the base URL to ewpire and pass this model id. Read the docs

curl https://ewpire.com/api/v1/chat/completions \
  -H "Authorization: Bearer $EWPIRE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"perplexity/sonar","messages":[{"role":"user","content":"Hello!"}]}'

The docs show how to list the models the API serves, with their capabilities and prices. Models in the docs

Similar models