Sonar Pro
Perplexity · released Mar 7, 2025
- Type
- Proprietary
- Input
- $3.00
- Output
- $15.00
- Cached
- Not published
List price · per 1M tokens · Perplexity at 200K context · source ↗
Our take
Written Aug 3, 2026Sonar Pro is a hosted-only research model from Perplexity that accepts text and images across a 200,000-token request limit. It is built for deep document work and citation-backed answers rather than benchmark leaderboard competition.
Pick this for long-document analysis at 200,000 tokens — research papers, legal discovery or codebase-wide review — or when you need image-to-text reasoning with search grounding. Use it if you are already inside the Perplexity ecosystem and want citation-backed answers. Skip it if you need measured quality scores to justify cost, if you want to self-host, or if you need verified speed data from more than one provider.
The case for it
- Extremely large request limit for deep document work: 200,000 tokens, well above the threshold often associated with extended-context tiers.
- Search-augmented reasoning with citation-backed answers through the Perplexity ecosystem.
The case against it
- No measured quality or reasoning scores in our data: no Elo, MMLU, GPQA or other task scores listed.
- Premium pricing with no verified performance advantage to justify cost against alternatives.
- Throughput only verified on one provider; speed data for the other tracked host is unmeasured.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Sonar Pro — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes Perplexity's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $3.00 in / $15.00 out
- Context served
- 200K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $3.00 / $15.00 | 200K | not measured | Unknown | Unknown | Unknown |
| Perplexity | $3.00 / $15.00 | 200K | 90 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✗ | ✗ |
| Perplexity | ✗ | ✗ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image->text
- Catalogue slug
- perplexity-sonar-pro