Ways to buy 1
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API | $2 | $8 | $2 / $8List price | n/a | List price |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $360.00 direct.
Helicone$360.00+0%
LiteLLM$360.00+0%
Vercel AI Gateway$360.00+0%
Requesty$378.00+5%
Eden AI$379.80+5.5%
OpenRouter$379.80+5.5%
Cloudflare AI GatewayNot offeredNot offered
Kong AI GatewayNot offeredNot offered
Neon AI GatewayNot offeredNot offered
PortkeyNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
Perplexity · 32K | $0.004 | Free | $0.004 / Free | $0.003 | 32K | Lab list price | · |
Perplexity · 32K | $0.03 | Free | $0.03 / Free | $0.022 | 32K | Lab list price | · |
Perplexity · 200K | $3 | $15 | $3 / $15 | $6 | 200K | Lab list price | · |
Perplexity · 128K | $2 | $8 | $2 / $8 | $3.5 | 128K | Lab list price | · |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
Google · 1MCheapest: $2.25 on Google Vertex AI (global-flex) | $2 | $12 | $2 / $12 | $4.5 | 1M | $2.25 on Google Vertex AI (global-flex) | · |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
About Sonar Reasoning Pro
Note: Sonar Pro pricing includes Perplexity search pricing.
Takes text, image in and returns text. First listed Sep 26, 2026. Up to 115K output tokens. Blended price $3.5 per 1M tokens at 3 input to 1 output. Model id sonar-reasoning-pro.
Price history
List price since Sep 26, 2026, from daily reads of the OpenRouter catalog.
Questions
How much does Sonar Reasoning Pro cost?
$2 per million input tokens and $8 per million output tokens.
What is the context window of Sonar Reasoning Pro?
128K tokens, with up to 115K tokens of output.