Aya Expanse 32B vs Qwen Plus Character (Japanese) vs Qwen-VL OCR
Too close to call on our weighted score (Qwen-VL OCR 36, Qwen Plus Character (Japanese) 36, Aya Expanse 32B 33). The right pick depends on what you value most.
Cohere
Aya Expanse 32B
33/100- ECI—
- Price$0.50 / $1.50
- Context128K
Alibaba (Qwen)
Qwen Plus Character (Japanese)
36/100- ECI—
- Price$0.50 / $1.40
- Context8K
Alibaba (Qwen)
Qwen-VL OCR
36/100- ECI—
- Price$0.72 / $0.72
- Context34K
Too close to call
It is close. Our weighted score puts them within a point (Qwen-VL OCR 36/100, Qwen Plus Character (Japanese) 36/100, Aya Expanse 32B 33/100), so choose by what matters most for your work: Qwen-VL OCR on price and Aya Expanse 32B for long inputs. 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-VL OCRQwen-VL OCR $0.72 · Qwen Plus Character (Japanese) $0.725 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
- Longest contextAya Expanse 32BAya Expanse 32B 128,000 · Qwen-VL OCR 34,096 · Qwen Plus Character (Japanese) 8,192 tokens
- Widest inputsQwen-VL OCRAya Expanse 32B: Text · Qwen Plus Character (Japanese): Text · Qwen-VL OCR: Text, Images
- Self-hostingAya Expanse 32BPublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Aya Expanse 32B | Qwen Plus Character (Japanese) | Qwen-VL OCR |
|---|---|---|---|---|
| Price | 50% | 56 | 57 | 57 |
| Inputs & features | 30% | 0 | 25 | 25 |
| Context window | 20% | 24 | 0 | 1 |
| Overall | 100% | 33/100 | 36/100 | 36/100 |
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 | $0.50 (best) | $0.50 (best) | $0.72 |
| Output | $1.50 | $1.40 | $0.72 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.75 | $0.725 | $0.72 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Alibaba API | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens (best) | 8,192 tokens | 34,096 tokens |
| Max output | 4,000 tokens | 512 tokens | 4,096 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenCC-BY-NC-4.0 | Proprietary | Proprietary |
| API model ID | c4ai-aya-expanse-32b | qwen-plus-character-ja | qwen-vl-ocr |
| API providers | 2 (best) | 1 | 1 |
| Released | Oct 24, 2024 | Jan 2024 | Oct 28, 2024 |
| Knowledge cutoff | — | Apr 2024 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Aya Expanse 32B$8.00
Qwen Plus Character (Japanese)$7.80
Qwen-VL OCR$8.64
Which should you choose?
Which is better: Aya Expanse 32B, Qwen Plus Character (Japanese) or Qwen-VL OCR?
It is close. Our weighted score puts them within a point (Qwen-VL OCR 36/100, Qwen Plus Character (Japanese) 36/100, Aya Expanse 32B 33/100), so choose by what matters most for your work: Qwen-VL OCR on price and Aya Expanse 32B for long inputs. 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, Aya Expanse 32B, Qwen Plus Character (Japanese) or Qwen-VL OCR?
Qwen-VL OCR is cheaper at $0.72 input / $0.72 output per million tokens (official Alibaba API price). Qwen Plus Character (Japanese) costs $0.50 input / $1.40 output per million tokens (official Alibaba API price); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.72 per million tokens for Qwen-VL OCR versus $0.725 for Qwen Plus Character (Japanese) (1× as much) and $0.75 for Aya Expanse 32B (1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Qwen Plus Character (Japanese) has not been scored yet and Qwen-VL OCR has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aya Expanse 32B, Qwen Plus Character (Japanese) and Qwen-VL OCR yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B and Qwen-VL OCR does not support tool calling, which most coding agents need.
Which has the bigger context window?
Aya Expanse 32B has the largest context window at 128,000 tokens, against 34,096 for Qwen-VL OCR and 8,192 for Qwen Plus Character (Japanese). Maximum output per response: Aya Expanse 32B up to 4,000, Qwen Plus Character (Japanese) up to 512, Qwen-VL OCR up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Aya Expanse 32B accepts text; Qwen Plus Character (Japanese) accepts text; Qwen-VL OCR accepts text and images. Qwen-VL OCR handles the widest range of inputs.
Are any of these open source?
Aya Expanse 32B publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Qwen Plus Character (Japanese) and Qwen-VL OCR is proprietary.
Which is newer?
Qwen-VL OCR is the newest, released Oct 28, 2024. Aya Expanse 32B came out Oct 24, 2024; Qwen Plus Character (Japanese) came out Jan 2024. Knowledge cutoff: Qwen Plus Character (Japanese) Apr 2024, Qwen-VL OCR Apr 2024.
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.