Sonar Deep Research
Perplexity · released Mar 7, 2025
- Type
- Closed
- Input
- $2.00
- Output
- $8.00
- Cached
- None held
List price · per 1M tokens · Perplexity at 128K context · source ↗
Our take
Written Sep 2, 2026Sonar Deep Research is Perplexity's proprietary text model built for long-document research, handling up to 128,000 tokens in a single request. It is available only through hosted access, with no downloadable weights or measured quality scores yet.
Pick this for research workflows on documents up to 128,000 tokens, or if you are already working inside the Perplexity ecosystem. Skip it if you need verified quality benchmarks, want to self-host or fine-tune, or require price competition between providers.
The case for it
- 128,000-token request limit — among the larger windows we hold for this model class.
- Identical pricing across both access paths, so there is no arbitrage hunt between them.
- Perplexity's own endpoint delivers 44 tokens per second, a concrete throughput figure.
The case against it
- No benchmark scores in our data, so research-grade output is unverified.
- Proprietary weights with no local deployment or fine-tuning possible.
- Parameter count undisclosed by the vendor.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
Perplexity, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Perplexity on 128K of context.
- per 1M tokens
- $2.00 in / $8.00 out
- Context served
- 128K
- Throughput
- ~36 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $8.00checked 2 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| PerplexityThrough OpenRouter | $2.00 / $8.00checked 2 hours ago | 128K115K max reply | 36 tok/s | No | No | Confirmed |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✗ | ✗ |
| PerplexityThrough OpenRouter | ✗ | ✗ | ✗ |
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
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, 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 does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak 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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- perplexity-sonar-deep-research