Sonar Deep Research
Perplexity · released Mar 7, 2025
- Type
- Proprietary
- Input
- $2.00
- Output
- $8.00
- Cached
- Not published
List price · per 1M tokens · Perplexity at 128K context · source ↗
Our take
Written Aug 3, 2026Sonar Deep Research is a proprietary text engine from Perplexity built for research workflows with a 128,000-token request limit. It is positioned for deep-document analysis rather than benchmark competition, with no independent quality scores in our data.
Pick this for long-document research where source material fits in a single 128,000-token pass, or for citation-backed workflows inside Perplexity's own ecosystem. Use it if you want predictable pricing across both tracked hosts. Skip it if you need measured quality data to justify the output rate, or if you require throughput guarantees beyond Perplexity's own API.
The case for it
- 128,000-token request limit fits long papers, reports or multi-source synthesis in one call.
- Identical pricing across both providers, so there is no markup on the secondary host.
- 52.5 tokens per second measured on Perplexity's own API.
The case against it
- No benchmark scores catalogued — chat, reasoning, coding and general knowledge are all unmeasured in our data.
- Throughput on the secondary provider is undisclosed.
- Premium output rate with no proven quality premium to justify it against unmeasured alternatives.
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 Deep Research — 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
- $2.00 in / $8.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.00 / $8.00 | 128K | not measured | Unknown | Unknown | Unknown |
| Perplexity | $2.00 / $8.00 | 128K | 56 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->text
- Catalogue slug
- perplexity-sonar-deep-research