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.
perplexity/sonarOpens 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
- ByteDance SeedSeed-2.0-Mini0.1241 in · 0.4965 out credits / 1M tokens
- ByteDance SeedSeed-2.0-Lite0.3103 in · 2.4824 out credits / 1M tokens
- ByteDance SeedSeed 2.1 Turbo0.6206 in · 3.1029 out credits / 1M tokens
- QwenQwen3.8 Omni Flash0.1862 in · 0.5834 out credits / 1M tokens
- QwenQwen3.8 27B0.0745 in · 2.7306 out credits / 1M tokens
- QwenQwen3.8 2.4T A95B2.4824 in · 7.4471 out credits / 1M tokens