Perplexity
Best for Research
Perplexity’s Sonar Reasoning Pro combines multi-step analysis with web retrieval. Distinct from the retired sonar-reasoning API identifier.
At a glance
API model ID: sonar-reasoning-pro
Capabilities & boundaries
Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
This is a reasoning model with multi-step analysis, not the old sonar-reasoning identifier. Avoid assuming that another provider’s effort settings apply. The documented response can include a think block before the answer, so structured-output integrations must handle that format.
Put it to work
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Use evidence and decision criteria, not a request for private internal reasoning.
Evaluate the infrastructure options below against the workload constraints I provide. Verify externally checkable claims using official sources. Present a concise rationale, a trade-off table, assumptions, and conditions that would change the recommendation. Flag missing measurements; do not invent benchmark results.
Workflow 02
Ask for a traceable conclusion with visible uncertainty.
Investigate these conflicting technical claims. Find the strongest primary evidence for each, identify version or methodology differences, and explain whether the conflict is real or only apparent. Cite the relevant passages by source link. State a confidence level and the evidence still needed before making a decision.
Workflow 03
Separate observations from inferred business conclusions.
Assess the market hypothesis below using recent primary sources and the decision criteria I provide. List supporting evidence, counterevidence, and important unknowns. Distinguish reported facts from your interpretation. Recommend a small validation experiment and explain what result would falsify the hypothesis.
Developer reference
These are Perplexity Sonar API reference prices, not EZ Ai Assist subscription prices.
View EZ Ai Assist plans| Token type | Price |
|---|---|
| Input | $2.00 |
| Output | $8.00 |
| Usage | Rate and unit |
|---|---|
| Low search context | $6.00per 1,000 requests |
| Medium search context | $10.00per 1,000 requests |
| High search context | $14.00per 1,000 requests |
Common questions
Consider Sonar Reasoning Pro for evidence-based comparisons and multi-step analysis that needs web retrieval. Ask for a concise rationale, source citations, and uncertainty; verify the recommendation against the underlying documents.
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.
Perplexity maps Sonar Reasoning Pro to low. Treat this as migration guidance, not an identical model or a guaranteed equivalent response. Recheck citations, quality, latency, and usage on representative tasks.
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.
No. Sonar Reasoning Pro uses sonar-reasoning-pro. Perplexity says sonar-reasoning was deprecated December 15, 2025; its specifications and pricing must not be substituted for the Pro model.
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.
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
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.
Same provider
Perplexity
Perplexity’s lightweight web-grounded Sonar model for focused questions, with citations and a documented transition to the Agent API.
Perplexity
Perplexity’s Sonar Pro supports deeper search and a 200K-token context. Explore its reference pricing and Agent API transition.
Perplexity
Perplexity’s Sonar Deep Research synthesizes broad web research into reports, with separate search, citation, and reasoning charges.