Project AURIONAI Use-Cases Research & Innovation
reasoning

Sonar Reasoning Pro

Perplexity search-grounded reasoning API model, described by OpenRouter as powered by DeepSeek R1; Perplexity ends Sonar Chat Completions support on 27 September 2026.

PerplexityPerplexitySonarFamily
Perplexity
Levelmodel
Classreasoning
Parametersnot in the notes
Context128,000
Released7 Mar 2025
Opennessproprietary
Runs onnot in the notes
Statusdeprecated

Lineage

distillproduct of
DeepSeek-R1 to DeepSeek-R1-Distill-Llama-70B: distill, high confidenceDeepSeek-R1 to DeepSeek-R1-Distill-Llama-8B: distill, high confidenceDeepSeek-R1 to DeepSeek-R1-Distill-Qwen-1.5B: distill, high confidenceDeepSeek-R1 to DeepSeek-R1-Distill-Qwen-14B: distill, high confidenceDeepSeek-R1 to DeepSeek-R1-Distill-Qwen-32B: distill, high confidenceDeepSeek-R1 to DeepSeek-R1-Distill-Qwen-7B: distill, high confidenceDeepSeek-R1 to Sonar Reasoning Pro: product of, low confidenceDeepSeek-R1DeepSeek-R1DeepSeek, Jan 2025DeepSeek-R1-Distill-Llama-70BDeepSeek-R1-Distill-Llama-…DeepSeek, Jan 2025DeepSeek-R1-Distill-Llama-8BDeepSeek-R1-Distill-Llama-…DeepSeek, Jan 2025DeepSeek-R1-Distill-Qwen-1.5BDeepSeek-R1-Distill-Qwen-1…DeepSeek, Jan 2025DeepSeek-R1-Distill-Qwen-14BDeepSeek-R1-Distill-Qwen-1…DeepSeek, Jan 2025DeepSeek-R1-Distill-Qwen-32BDeepSeek-R1-Distill-Qwen-3…DeepSeek, Jan 2025DeepSeek-R1-Distill-Qwen-7BDeepSeek-R1-Distill-Qwen-7BDeepSeek, Jan 2025Sonar Reasoning ProSonar Reasoning ProPerplexity, Mar 2025
DeepSeekDeepSeek-R1 is the parent (product of)low confidencepress claim
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 8 models. Confidence and evidence are the notes' own.

R&D Topics

Reasoning via large-scale RLproduced byRetrieval-augmented generation (RAG)produced by

Identity

Developer
Perplexity
Family
Sonar
Released
7 Mar 2025 sourcesregistry date
Weights published
–
Record checked
11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
128,000 tokens
Input
text, image
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
not in the notes sources
Access routes
API
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. docs.perplexity.ai/getting-started/models/models/sonar-reasoning... https://docs.perplexity.ai/getting-started/models/models/sonar-reasoning-pro
  2. openrouter.ai/api/v1/models https://openrouter.ai/api/v1/models
  3. docs.perplexity.ai/getting-started/models https://docs.perplexity.ai/getting-started/models

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Sonar Reasoning Pro", https://aurion.semai.id/models/perplexity-sonar-reasoning-pro/, records of October 2026.