Command A vs Sonar vs Sonar Deep Research
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
Cohere
Command A
38/100- ECI—
- Price$2.50 / $10.00
- Context256K
Perplexity
Sonar
13/100- ECI—
- Price$1.00 / $1.00
- Context128K
Perplexity
Sonar Deep Research
19/100- ECI—
- Price$2.00 / $8.00
- Context128K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Command A 38/100, Sonar Deep Research 19/100, Sonar 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 · Command A $4.38 per 1M tokens (3:1 blend)
- Longest contextCommand ACommand A 256,000 · Sonar 128,000 · Sonar Deep Research 128,000 tokens
- Widest inputsSame inputsCommand A: Text · Sonar: Text · Sonar Deep Research: Text
- Self-hostingCommand APublishes downloadable weights
| Measure | Weight | Command A | Sonar | Sonar Deep Research |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 0 | 10 |
| Context window | 40% | 43 | 32 | 32 |
| Specs only | 100% | 38/100 | 13/100 | 19/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.50 | $1.00 (best) | $2.00 |
| Output | $10.00 | $1.00 (best) | $8.00 |
| Cached input | — | — | — |
| Blended (3:1) | $4.38 | $1.00 (best) | $3.50 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Official Perplexity API | Official Perplexity API |
| Limits | |||
| Context window | 256,000 tokens (best) | 128,000 tokens | 128,000 tokens |
| Max output | 8,000 tokens | 4,096 tokens | 32,768 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yesminimal · low · medium · high |
| Tool calling | Yes | No | No |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | command-a-03-2025 | sonar | sonar-deep-research |
| API providers | 7 | 9 (best) | 5 |
| Released | Mar 13, 2025 | Jan 1, 2024 | Feb 1, 2025 |
| Knowledge cutoff | Jun 1, 2024 | 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.
Command A$45.00
Sonar$12.00
Sonar Deep Research$36.00
Which should you choose?
Which is better: Command A, Sonar or Sonar Deep Research?
There is not enough shared capability evidence to name an overall winner. The scores (Command A 38/100, Sonar Deep Research 19/100, Sonar 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Command A, 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); Command A costs $2.50 input / $10.00 output per million tokens (official Cohere 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) and $4.38 for Command A (4.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Command A has not been scored 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 Command A, 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?
Command A has the largest context window at 256,000 tokens, against 128,000 for Sonar and 128,000 for Sonar Deep Research. Maximum output per response: Command A up to 8,000, Sonar up to 4,096, Sonar Deep Research up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Command A accepts text; Sonar accepts text; Sonar Deep Research accepts text. They handle the same number of input types.
Are any of these open source?
Command A publishes its weights and can be self-hosted; Sonar and Sonar Deep Research is proprietary.
Which is newer?
Command A is the newest, released Mar 13, 2025. Sonar Deep Research came out Feb 1, 2025; Sonar came out Jan 1, 2024. Knowledge cutoff: Command A Jun 1, 2024, Sonar Sep 1, 2025, Sonar Deep Research Jan 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 18, 2026.