Perplexity logo

Perplexity: Sonar Reasoning Pro

Web-grounded Sonar for multi-step research questions that need cited reasoning

Source-linked sonar-reasoning Closed weights Released 2024-01-01
API record Report
InputT
OutputT
Input price$2/M
Output price$8/M
Context128K
Max output4.096K
Providers9
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Sonar Reasoning Pro
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
AnyAPI perplexity/sonar-reasoning-pro 128K 4.096K Reasoning Docs ↗
Vercel AI Gateway perplexity/sonar-reasoning-pro 127K 8K Reasoning Docs ↗
Eden AI perplexityai/sonar-reasoning-pro 128K 4.096K $2 $8 Reasoning Docs ↗
Kilo Gateway perplexity/sonar-reasoning-pro 128K 115.2K $2 $8 Reasoning Docs ↗
LLM Gateway perplexity/sonar-reasoning-pro 128K 4.096K $2 $8 JSON Docs ↗
DevPass (LLM Gateway) sonar-reasoning-pro 128K 4.096K $2 $8 Reasoning Docs ↗
Opper perplexity/sonar-reasoning-pro 128K 4.096K $2 $8 Reasoning Docs ↗
Perplexity sonar-reasoning-pro 128K 4.096K $2 $8 Reasoning Docs ↗
OpenRouter perplexity/sonar-reasoning-pro 128K 115.2K $2 $8 Reasoning Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $2/M

Across 7 priced providers

Median input $2/M

Midpoint of listed rates

Highest input $2/M

Same as the lowest listed rate

Output range $8 – $8

Per million output tokens

Eden AI $2/M
Kilo Gateway $2/M
LLM Gateway $2/M
DevPass (LLM Gateway) $2/M
Opper $2/M
Perplexity $2/M
OpenRouter $2/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

7 providers list the identical $2 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 127K to 128K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
× Tool calling No
Structured output Yes
Attachments Yes
Vision input Yes
× Open weights No
Creator
Perplexity
Model family
sonar-reasoning
Knowledge cutoff
2025-09-01
License
Not documented
Release date
2024-01-01
Model ID
perplexity/sonar-reasoning-pro
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Max Output Tokens115200 → 4096
Max Output Tokens4096 → 115200
Max Output Tokens115200 → 4096
Max Output Tokens4096 → 115200
Max Output Tokens115200 → 4096
Max Output Tokens4096 → 115200
Max Output Tokens115200 → 4096
Max Output Tokens4096 → 115200
Max Output Tokens115200 → 4096
Max Output Tokens4096 → 115200
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/perplexity/sonar-reasoning-pro
curl
curl "https://model.kyssta.lol/api/v1/models/perplexity/sonar-reasoning-pro"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Sonar Reasoning Pro?

Web-grounded Sonar for multi-step research questions that need cited reasoning. It is published by Perplexity and catalogued here from Models.dev.

How much does Sonar Reasoning Pro cost?

Listed input pricing starts at $2 per million tokens from Eden AI.

What is the context length of Sonar Reasoning Pro?

Sonar Reasoning Pro accepts up to 128K tokens of context and returns up to 4.096K output tokens.

Does Sonar Reasoning Pro support tool calling and structured output?

Provider catalogs list support for structured output, and image input.

Which providers serve Sonar Reasoning Pro?

9 providers list this model: AnyAPI, Vercel AI Gateway, Eden AI, Kilo Gateway, LLM Gateway, DevPass (LLM Gateway) and 3 more.

Are the weights for Sonar Reasoning Pro open?

No. This model is served through hosted APIs only.

When was Sonar Reasoning Pro released?

The catalog records a release date of 2024-01-01, last verified Sep 11, 2026.

More models from Perplexity

View all →