Sonar API Pricing
Retired September 27, 2026: Perplexity ended Sonar Chat Completions support on that date. Synchronous sonar requests are being reformulated as Agent API requests, rolling out by model, and asynchronous ones are no longer accepted; Perplexity's suggested starting point is the Agent API fast preset. The rates below are the last the Sonar API listed, kept for invoice checks. Sonar was Perplexity's standard web-grounded answer model. The Sonar API listed it at $1/M input and $1/M output, with request and search fees billed separately. Checked against Perplexity's migration guide.
Sonar API cost calculator.
Live calculator pre-loaded with current Sonar token rates. Perplexity request and search fees are documented in the scenarios and FAQ, because they are separate from token pricing.
Sonar cost on real workloads.
Web answer low context
Market check medium context
Evidence-rich answer
Daily topic monitor
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Sonar Current | $1.00 | $1.00 | $1.00 agentic 92/8 | not listed | Low-cost web-grounded answers |
| Sonar (Agent API) | $0.25 cache $0.0625 | $2.50 | $0.289 −3.5× | not listed | Perplexity's per-token model on the Agent API |
| Sonar Pro | $3.00 | $15.00 | $3.96 retired | not listed | Higher-quality search answers |
| Sonar Reasoning Pro | $2.00 | $8.00 | $2.48 retired | not listed | Reasoned web research |
| Sonar Deep Research | $2.00 | $8.00 | $2.48 retired | not listed | Multi-step deep research |
| Aya Expanse 32B | $0.50 | $1.50 | $0.58 −42% | 128K | Multilingual generation and translation |
| Reka Edge | $0.10 | $0.10 | $0.10 −10× | 16K | Lowest-cost Reka chat |
Sonar API pricing FAQ.
Practical Sonar pricing questions, with public list prices separated from assumptions and add-on fees.
Q · 01 What happened to Sonar? +
sonar the suggested starting point is the Agent API fast preset. Perplexity does not say which rates a reformulated request bills at. Its own model on the Agent API, Sonar (Agent API), lists at $0.25/M input and $2.50/M output, with tools billed per call.Q · 02 What is Sonar priced at? +
$1/M input and $1/M output on Perplexity's official pricing page, verified 2026-06-14.Q · 03 Is prompt caching priced separately? +
$1/M, instead of inventing a discount.Q · 04 How is the effective price calculated? +
$1/M.Q · 05 Does this include every possible fee? +
Q · 06 Are there free trials or production keys? +
Q · 07 Which API model ID should I use? +
sonar belonged to the Sonar Chat Completions API, which Perplexity stopped supporting on September 27, 2026. Its suggested starting point is the Agent API fast preset; Perplexity's own per-token model there is perplexity/sonar, priced on the Sonar (Agent API) page.