What is the cheapest Perplexity model?

pplx-decider-flash-v1.2 is currently Perplexity's cheapest paid tracked model at $0.01 per 1M input tokens and $0 per 1M output tokens.

How many Perplexity models are tracked?

3 current Perplexity models are tracked, each linked to the official pricing page. The dataset is refreshed twice daily.

Does Perplexity offer cached-input pricing?

Perplexity lists cached-input (prompt-caching) prices for 1 tracked models — cached input is billed at a discount when a prompt prefix repeats.

Perplexity

Commercial provider · 3 models tracked · Founded 2022

Search-augmented AI from Perplexity. Its Sonar search model is sold on the Agent API at $0.25/1M input and $2.50/1M output tokens, with each web search billed separately; the older Sonar models were retired on 2026-09-27.

Perplexity pricing at a glanceNovember 2026 · $ per 1M tokens

Perplexity API pricing (November 2026): 3 current models range from $0.010 to $0.250 per 1M input tokens and $2.50 to $2.50 per 1M output tokens. The cheapest paid model is pplx-decider-flash-v1.2 at $0.010/1M input; the priciest is Sonar (Agent API) at $0.250/1M input / $2.50 output. Every price links to Perplexity's official pricing page and refreshes twice daily.

Models3

Input range$0.010–$0.250

Output range$2.50–$2.50

Cached-input tiers1

Today's Perplexity prices

3 models · cheapest blended first

Sorted by blended cost (cheapest first). Prices per 1M tokens, November 2026 — every price links to Perplexity's official pricing page.

Current Perplexity model prices per 1M tokens, sorted by blended cost
Model	Blended*	Input	Output	Cached in	Context	Status
pplx-decider-flash-v1.2	$0.007	$0.010	$0	—	262K	Current
pplx-decider-v1.2	$0.015	$0.020	$0	—	262K	Current
Sonar (Agent API)	$0.813	$0.250	$2.50	$0.063	—	Current

* Blended = (3×input + 1×output) ÷ 4 $/1M tokens · cheap · mid · expensive MODELPRICEWATCH.COM · 2026-11-07

Quick stats

Models tracked: 3
Type: commercial
Founded: 2022
Cheapest model: pplx-decider-flash-v1.2
Cheapest blended: $0.007/M

Open-weight models

2 open-weight models available from this provider.

pplx-decider-v1.2

$0.020/M in · 262K ctx

pplx-decider-flash-v1.2

$0.010/M in · 262K ctx

Try Perplexity

Get started

Run it yourself

Self-host Perplexity's open-weight models

These models ship with open weights, so you can serve them yourself on rented GPUs instead of paying per-token API prices — often cheaper at scale.

RunPod →

Rent GPUs by the second and serve any open-weight model yourself.

Novita AI →

Serverless open-model inference billed per token — no GPU ops.

Vast.ai →

GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.