Sonar
Perplexity · released Jan 27, 2025
- Type
- Proprietary
- Input
- $1.00
- Output
- $1.00
- Cached
- Not published
List price · per 1M tokens · Perplexity at 127K context · source ↗
Our take
Written Aug 2, 2026Sonar is Perplexity's lightweight search-augmented model that accepts text and images and handles up to 127,072 tokens in a single request. It is priced identically across its two hosts, making it a straightforward choice for Perplexity ecosystem work where search grounding matters more than measured benchmark scores.
Pick this for Perplexity ecosystem integration where search grounding is the priority, or for low-cost image-capable inference when 127,072 tokens of context suffices. Skip it if you need independently verified quality data, or if you want to shop between hosts for a better price.
The case for it
- Identical pricing across both tracked hosts removes cost-arbitrage complexity.
- Documented throughput of 112 tokens per second on the direct host.
The case against it
- No benchmark scores in our catalogue: chat, reasoning, coding and multimodal performance are all unmeasured.
- Throughput on the secondary host is unverified in our data.
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 — 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
- $1.00 in / $1.00 out
- Context served
- 127K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.00 / $1.00 | 127K | not measured | Unknown | Unknown | Unknown |
| Perplexity | $1.00 / $1.00 | 127K | 52 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