Perplexity — pricing & performance
Models served
5
of 947 tracked models
Mean output speed
60
tokens per second, averaged over
5 measured endpoints
5 measured endpoints
Mean latency
18.3s
time to first token, averaged over
5 measured endpoints
5 measured endpoints
Cheapest blended
$1.00
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Perplexity
Median output tokens per second for all 5 models on Perplexity with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 5 of 5 models⇩
The Known Good
5 models on Perplexity
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Perplexity: Sonar
|
Perplexity | $1.00 | $1.00 | $1.00 | 71 | 1.7s | 127k |
|
Perplexity: Sonar Deep Research
|
Perplexity | $2.00 | $8.00 | $3.50 | 4 | 76.8s | 128k |
|
Perplexity: Sonar Pro
|
Perplexity | $3.00 | $15.00 | $6.00 | 101 | 1.9s | 200k |
|
Perplexity: Sonar Pro Search
|
Perplexity | $3.00 | $15.00 | $6.00 | 100 | 1.4s | 200k |
|
Perplexity: Sonar Reasoning Pro
|
Perplexity | $2.00 | $8.00 | $3.50 | 23 | 9.5s | 128k |
The Known Good
Source. Prices, endpoint availability and throughput for Perplexity are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.