Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
Supported API features and tools
Web-grounded answers with citations
Search-result metadata for inspecting sources
Streaming response support
A documented 128K-token context
Before you choose
Not designed for exhaustive research or complex multi-step reasoning.
Citations can be incomplete, outdated, or fail to support the associated claim.
The documented Sonar API is in migration; do not assume its old behavior or price is unchanged by a replacement.
Non-reasoning model
The documented Sonar model is a non-reasoning search model. Do not treat its search-context size as a reasoning-effort level. During migration, check which Agent API configuration handles your request.
Perplexity’s migration guide maps Sonar to the Agent API fast preset. Presets and underlying model selections can change; test results after migrating.
The reviewed model card does not publish a maximum output-token limit or training cutoff. Web access does not make an unknown training cutoff a current date.
This guide’s examples use text. Check the selected endpoint’s current input and output support rather than assuming full parity with another Sonar or Agent API configuration.
Put it to work
Start with a more useful prompt.
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Check a product announcement
Ask a narrow current question with dated primary evidence.
Find the official announcement and release notes for the product update named below. Report what launched, the announcement date, and any stated rollout limits. Cite the primary source for each point. Separate generally available features from previews and say when a detail cannot be confirmed.
Workflow 02
Resolve a terminology question
Prefer a short answer backed by authoritative documentation.
Explain the difference between these two technical terms using their official documentation. Give one practical example for each and cite the relevant definitions. Keep the answer under 250 words. If the terms vary by product or version, identify that scope instead of presenting one universal definition.
Workflow 03
Verify a public support policy
Read the stated policy rather than infer eligibility.
Find the current official support-policy page for this software product. Extract supported versions, end-of-support dates, and the published upgrade path with source links. Note when the page was updated. Do not infer that a specific customer contract is covered by the public policy.
Developer reference
Perplexity API pricing
These are Perplexity Sonar API reference prices, not EZ Ai Assist subscription prices.
Published Sonar reference · USD per 1,000,000 tokens
Token type
Price
Input
$1.00
Output
$1.00
Additional API fees · USD
Usage
Rate and unit
Low search context
$5.00per 1,000 requests
Medium search context
$8.00per 1,000 requests
High search context
$12.00per 1,000 requests
These are the published Sonar reference rates, not an estimate of migrated Agent API costs or OpenRouter resale prices. Check the current endpoint, preset, and response usage before budgeting.
Add the applicable search-context request fee to token charges. Search context controls retrieved material, not reasoning effort.
Perplexity recommends Agent API for new projects. Migration can change both execution and billing; retain these rates as a clearly scoped Sonar reference.
Common questions
A few things worth knowing.
When should I consider Sonar?
Use Sonar-style search for a focused factual question or a concise topic update where cited web evidence matters more than exhaustive analysis. Keep the question bounded and check the sources; search-backed output can still be wrong.
What changed with the Sonar API?
Perplexity says Sonar Chat Completions support ended September 27, 2026. Synchronous and streaming calls continue through a gradual translation to Agent API requests; async Sonar calls are no longer supported. This does not establish whether EZ Ai Assist or a reseller exposes a particular model.
Which Agent API preset is the documented replacement?
Perplexity maps Sonar to fast. Treat this as migration guidance, not an identical model or a guaranteed equivalent response. Recheck citations, quality, latency, and usage on representative tasks.
Are search fees included in token prices?
No. The published Sonar table adds request fees based on search-context size. The low, medium, and high rows are per 1,000 requests, not per million tokens.
Can I trust every citation?
No. Open the cited pages and confirm they support the exact claim, concern the correct version, and are recent enough. A citation is a starting point for verification, not a guarantee of accuracy.
What do the limits on this page mean?
The model card lists a 128K-token context. It does not establish a maximum output limit or training cutoff in the reviewed documentation. Integration limits may be lower, and search-backed answers still need checking.
Are these fees part of my EZ Ai Assist subscription?
No. The reference table describes Perplexity’s documented API billing. EZ Ai Assist plans are separate, and app availability must be checked in the workspace. These prompts are original starting points, not verified benchmark outputs.
Check the source
Official documentation
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.