Sonar vs Sonar Deep Research
Sonar comes out ahead, 30 to 20 on our weighted score, and it is the cheaper option too.
- Our pick
PerplexitySonar
30/100- ECI—
- Price$1.00 / $1.00
- Context128K
- Perplexity
Sonar Deep Research
20/100- ECI—
- Price$2.00 / $8.00
- Context128K
Add a model
Make it a three-way comparison.
Sonar is our pick
Sonar is the better all-round choice, scoring 30/100 against Sonar Deep Research (20). It leads on price. Sonar Deep Research wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceSonarSonar $1.00 · Sonar Deep Research $3.50 per 1M tokens (3:1 blend)
- Longest contextAbout the sameSonar 128,000 · Sonar Deep Research 128,000 tokens
- Widest inputsSame inputsSonar: Text · Sonar Deep Research: Text
- Self-hostingNo open weightsBoth are available only through APIs
| Measure | Weight | Sonar | Sonar Deep Research |
|---|---|---|---|
| Price | 50% | 50 | 24 |
| Inputs & features | 30% | 0 | 10 |
| Context window | 20% | 24 | 24 |
| Overall | 100% | 30/100 | 20/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | SonarPerplexity | Sonar Deep ResearchPerplexity |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | $1.00 (best) | $2.00 |
| Output | $1.00 (best) | $8.00 |
| Cached input | — | — |
| Blended (3:1) | $1.00 (best) | $3.50 |
| Long-context rate | Same rate | Same rate |
| Price source | Official Perplexity API | Official Perplexity API |
| Limits | ||
| Context window | 128,000 tokens | 128,000 tokens |
| Max output | 4,096 tokens | 32,768 tokens (best) |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | No | Yesminimal · low · medium · high |
| Tool calling | No | No |
| Structured output | No | No |
| Availability | ||
| Weights | Proprietary | Proprietary |
| API model ID | sonar | sonar-deep-research |
| API providers | 6 (best) | 3 |
| Released | Jan 1, 2024 | Feb 1, 2025 |
| Knowledge cutoff | Sep 1, 2025 | Jan 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Sonar$12.00
- Sonar Deep Research$36.00
Which should you choose?
Which is better: Sonar or Sonar Deep Research?
Sonar is the better all-round choice, scoring 30/100 against Sonar Deep Research (20). It leads on price. Sonar Deep Research wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Sonar or Sonar Deep Research?
Sonar is cheaper at $1.00 input / $1.00 output per million tokens (official Perplexity API price). Sonar Deep Research costs $2.00 input / $8.00 output per million tokens (official Perplexity API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for Sonar versus $3.50 for Sonar Deep Research (3.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Sonar has not been scored yet and Sonar Deep Research has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sonar and Sonar Deep Research yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sonar and Sonar Deep Research does not support tool calling, which most coding agents need.
Which has the bigger context window?
Sonar and Sonar Deep Research share the same 128,000-token context window. Maximum output per response: Sonar up to 4,096, Sonar Deep Research up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Sonar accepts text; Sonar Deep Research accepts text. They handle the same number of input types.
Are any of these open source?
No. Sonar and Sonar Deep Research are proprietary and only available through APIs and apps.
Which is newer?
Sonar Deep Research is the newest, released Feb 1, 2025. Sonar came out Jan 1, 2024. Knowledge cutoff: Sonar Sep 1, 2025, Sonar Deep Research Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
