LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Sonar Reasoning Pro

perplexity·perplexity/sonar-reasoning-pro·Deprecated·Closed·sonar-reasoning series
Web-grounded Sonar for multi-step research questions that need cited reasoning

Specs & pricing

Input / output per 1M tokens
Official price·Perplexity
$2.00 / $8.00
Blended $3.50 · Cache read —
Lowest paid·PerplexityFirst-party
$2.00 / $8.00
Blended $3.50 · 1× spread
Context
128,000
Output limit
4,096
Knowledge cutoff
2025-09-01
Released / updated
2024-01-01 / 2025-09-01
Capabilities
✓ ReasoningTool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Sonar Reasoning Pro by perplexity is offered by 7 providers on this page. Public prices are shown for 6 of them. Its official list price is $2.00 per 1M input tokens and $8.00 per 1M output tokens. No paid channel is priced below the official list price.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 127,000 to 128,000, so the usable window depends on the provider you pick. It supports reasoning. Accepted input modalities are Text and Image. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-09-01.

Available at 7 providers6 with public prices

  • ProviderInput / Output
  • PerplexityOfficialFirst-party
    $2.00 / $8.00
    Context 128,000Output limit 4,096deprecated
  • OpenRouterGateway
    $2.00 / $8.00
    Context 128,000Output limit 115,200
  • OpperGateway
    $2.00 / $8.00
    Context 128,000Output limit 4,096
  • Eden AIGateway
    $2.00 / $8.00
    Context 128,000Output limit 4,096
  • Kilo GatewayGateway
    $2.00 / $8.00
    Context 128,000Output limit 115,200
  • HeliconeGateway
    $2.00 / $8.00
    Context 127,000 ⚠Output limit 4,096
  • AnyAPIGateway
    — / —
    Context 128,000Output limit 4,096hostTable.undisclosed
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PerplexityOfficialFirst-party$2.00$8.00——128,0004,096deprecated
OpenRouterGateway$2.00$8.00——128,000115,200
OpperGateway$2.00$8.00——128,0004,096
Eden AIGateway$2.00$8.00——128,0004,096
Kilo GatewayGateway$2.00$8.00——128,000115,200
HeliconeGateway$2.00$8.00——127,000 ⚠4,096
AnyAPIGateway————128,0004,096hostTable.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.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = highToggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 1 of 7 providers.

2 / 7 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Perplexity · Official$800.00
2OpenRouter$800.00
3Opper$800.00
4Eden AI$800.00
5Kilo Gateway$800.00
6Helicone$800.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$8.00$02026-08-052026-09-02
2026-09-02Input list $2.00Output list $8.00Min blended $3.50

Related models

Perplexity Sonar Reasoningsame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60Kimi K2.6cheaper alternative$0.95 / $4.00GPT-5.6 Lunacheaper alternative$0.20 / $1.20Sonar Prosame lab$3.00 / $15.00Decider Flash V1.3same lab—
Data partly from models.dev (MIT) · Perplexity official docs ↗