← Model list
Sonar Reasoning Pro
perplexity·perplexity/sonar-reasoning-pro-2·GA·Closed·sonar-reasoning series
Web-grounded Sonar for multi-step research questions that need cited reasoning
At a glance
Official price$2.00 / $8.00 per 1M
Cache read — · Perplexity
Lowest paid$2.00 / $8.00
OpenRouter Gateway · 1× spread
Context128,000
⚠ Providers report 127,000–128,000; the table below is authoritative
Output limit4,096
Capabilities
✓ ReasoningTool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff2025-09-01
Released / updated2024-01-01 / 2025-09-01
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence18
Value5
Coding—
Agentic—
Output speed—
TTFT—
Value formulaIQ 18 ÷ min blended $3.500 = 5
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 6 providers4 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| OpenRouter perplexity/sonar-reasoning-pro | Gateway | $2.00 | $8.00 | — | — | 128,000 | 128,000 | |
| PerplexityOfficial sonar-reasoning-pro | First-party | $2.00 | $8.00 | — | — | 128,000 | 4,096 | |
| Eden AI perplexityai/sonar-reasoning-pro | Gateway | $2.00 | $8.00 | — | — | 128,000 | 4,096 | |
| DevPass (LLM Gateway) sonar-reasoning-pro | Gateway | $2.00 | $8.00 | — | — | 128,000 | 4,096 | |
| AnyAPI perplexity/sonar-reasoning-pro | Gateway | — | — | — | — | 128,000 | 4,096 | hostTable.undisclosed |
| Vercel AI Gateway perplexity/sonar-reasoning-pro | Cloud | — | — | — | — | 127,000 ⚠ | 8,000 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1OpenRouter$800.00
2Perplexity · Official$800.00
3Eden AI$800.00
4DevPass (LLM Gateway)$800.00
Switch to OpenRouter to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = minimaleffort = loweffort = mediumeffort = high
2 / 6 providers expose no reasoning control (reasoning_options: []).
Related models
Perplexity Reasoning Prosame series$2.00 / $8.00Sonar Reasoning Pro (Perplexity)same series$2.00 / $8.00Perplexity Sonar Reasoning Prosame series$2.00 / $8.00GPT OSS 120Bcheaper alternative$1.00 / $4.20Kimi K2.6cheaper alternative$0.95 / $4.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended