Qwen-MT Plus vs Qwen Plus Character (Japanese) vs Sonar Deep Research
Qwen Plus Character (Japanese) comes out ahead, 36 to 20 and 12 on our weighted score, and it is the cheaper option too.
Alibaba (Qwen)Qwen-MT Plus
12/100- ECI—
- Price$2.46 / $7.37
- Context16K
- Our pickAlibaba (Qwen)
Qwen Plus Character (Japanese)
36/100- ECI—
- Price$0.50 / $1.40
- Context8K
PerplexitySonar Deep Research
20/100- ECI—
- Price$2.00 / $8.00
- Context128K
Qwen Plus Character (Japanese) is our pick
Qwen Plus Character (Japanese) is the better all-round choice, scoring 36/100 against Sonar Deep Research (20) and Qwen-MT Plus (12). It leads on price and inputs & features. Sonar Deep Research wins on context window. 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 priceQwen Plus Character (Japanese)Qwen Plus Character (Japanese) $0.725 · Sonar Deep Research $3.50 · Qwen-MT Plus $3.69 per 1M tokens (3:1 blend)
- Longest contextSonar Deep ResearchSonar Deep Research 128,000 · Qwen-MT Plus 16,384 · Qwen Plus Character (Japanese) 8,192 tokens
- Widest inputsSame inputsQwen-MT Plus: Text · Qwen Plus Character (Japanese): Text · Sonar Deep Research: Text
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Qwen-MT Plus | Qwen Plus Character (Japanese) | Sonar Deep Research |
|---|---|---|---|---|
| Price | 50% | 23 | 57 | 24 |
| Inputs & features | 30% | 0 | 25 | 10 |
| Context window | 20% | 0 | 0 | 24 |
| Overall | 100% | 12/100 | 36/100 | 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 | Qwen-MT PlusAlibaba (Qwen) | Qwen Plus Character (Japanese)Alibaba (Qwen) | Sonar Deep ResearchPerplexity |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.46 | $0.50 (best) | $2.00 |
| Output | $7.37 | $1.40 (best) | $8.00 |
| Cached input | — | — | — |
| Blended (3:1) | $3.69 | $0.725 (best) | $3.50 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official Alibaba API | Official Perplexity API |
| Limits | |||
| Context window | 16,384 tokens | 8,192 tokens | 128,000 tokens (best) |
| Max output | 8,192 tokens | 512 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 | No | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | qwen-mt-plus | qwen-plus-character-ja | sonar-deep-research |
| API providers | 1 | 1 | 3 (best) |
| Released | Jan 2025 | Jan 2024 | Feb 1, 2025 |
| Knowledge cutoff | Apr 2024 | Apr 2024 | 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.
- Qwen-MT Plus$39.34
- Qwen Plus Character (Japanese)$7.80
- Sonar Deep Research$36.00
Which should you choose?
Which is better: Qwen-MT Plus, Qwen Plus Character (Japanese) or Sonar Deep Research?
Qwen Plus Character (Japanese) is the better all-round choice, scoring 36/100 against Sonar Deep Research (20) and Qwen-MT Plus (12). It leads on price and inputs & features. Sonar Deep Research wins on context window. 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, Qwen-MT Plus, Qwen Plus Character (Japanese) or Sonar Deep Research?
Qwen Plus Character (Japanese) is cheaper at $0.50 input / $1.40 output per million tokens (official Alibaba API price). Sonar Deep Research costs $2.00 input / $8.00 output per million tokens (official Perplexity API price); Qwen-MT Plus costs $2.46 input / $7.37 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.725 per million tokens for Qwen Plus Character (Japanese) versus $3.50 for Sonar Deep Research (4.8× as much) and $3.69 for Qwen-MT Plus (5.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen-MT Plus has not been scored yet, Qwen Plus Character (Japanese) 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 Qwen-MT Plus, Qwen Plus Character (Japanese) 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 Qwen-MT Plus and Sonar Deep Research does not support tool calling, which most coding agents need.
Which has the bigger context window?
Sonar Deep Research has the largest context window at 128,000 tokens, against 16,384 for Qwen-MT Plus and 8,192 for Qwen Plus Character (Japanese). Maximum output per response: Qwen-MT Plus up to 8,192, Qwen Plus Character (Japanese) up to 512, Sonar Deep Research up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Qwen-MT Plus accepts text; Qwen Plus Character (Japanese) accepts text; Sonar Deep Research accepts text. They handle the same number of input types.
Are any of these open source?
No. Qwen-MT Plus, Qwen Plus Character (Japanese) 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. Qwen-MT Plus came out Jan 2025; Qwen Plus Character (Japanese) came out Jan 2024. Knowledge cutoff: Qwen-MT Plus Apr 2024, Qwen Plus Character (Japanese) Apr 2024, 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.
