Aya Expanse 32B vs Qwen2.5-VL 72B Instruct vs Qwen-VL OCR
Qwen-VL OCR comes out ahead, 36 to 33 and 30 on our weighted score, and it is the cheaper option too.
CohereAya Expanse 32B
33/100- ECI—
- Price$0.50 / $1.50
- Context128K
Alibaba (Qwen)Qwen2.5-VL 72B Instruct
30/100- ECI—
- Price$2.80 / $8.40
- Context131K
- Our pickAlibaba (Qwen)
Qwen-VL OCR
36/100- ECI—
- Price$0.72 / $0.72
- Context34K
Qwen-VL OCR is our pick
Qwen-VL OCR is the better all-round choice, scoring 36/100 against Aya Expanse 32B (33) and Qwen2.5-VL 72B Instruct (30). Qwen2.5-VL 72B Instruct 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 priceQwen-VL OCRQwen-VL OCR $0.72 · Aya Expanse 32B $0.75 · Qwen2.5-VL 72B Instruct $4.20 per 1M tokens (3:1 blend)
- Longest contextQwen2.5-VL 72B InstructQwen2.5-VL 72B Instruct 131,072 · Aya Expanse 32B 128,000 · Qwen-VL OCR 34,096 tokens
- Widest inputsQwen2.5-VL 72B Instruct and Qwen-VL OCRAya Expanse 32B: Text · Qwen2.5-VL 72B Instruct: Text, Images · Qwen-VL OCR: Text, Images
- Self-hostingAya Expanse 32B and Qwen2.5-VL 72B InstructPublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Aya Expanse 32B | Qwen2.5-VL 72B Instruct | Qwen-VL OCR |
|---|---|---|---|---|
| Price | 50% | 56 | 20 | 57 |
| Inputs & features | 30% | 0 | 50 | 25 |
| Context window | 20% | 24 | 24 | 1 |
| Overall | 100% | 33/100 | 30/100 | 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 | Aya Expanse 32BCohere | Qwen2.5-VL 72B InstructAlibaba (Qwen) | Qwen-VL OCRAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.50 (best) | $2.80 | $0.72 |
| Output | $1.50 | $8.40 | $0.72 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.75 | $4.20 | $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 | 131,072 tokens (best) | 34,096 tokens |
| Max output | 4,000 tokens | 8,192 tokens (best) | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | 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 | Open | Proprietary |
| API model ID | c4ai-aya-expanse-32b | qwen2-5-vl-72b-instruct | qwen-vl-ocr |
| API providers | 2 (best) | 1 | 1 |
| Released | Oct 24, 2024 | Sep 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
- Qwen2.5-VL 72B Instruct$44.80
- Qwen-VL OCR$8.64
Which should you choose?
Which is better: Aya Expanse 32B, Qwen2.5-VL 72B Instruct or Qwen-VL OCR?
Qwen-VL OCR is the better all-round choice, scoring 36/100 against Aya Expanse 32B (33) and Qwen2.5-VL 72B Instruct (30). Qwen2.5-VL 72B Instruct 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, Aya Expanse 32B, Qwen2.5-VL 72B Instruct or Qwen-VL OCR?
Qwen-VL OCR is cheaper at $0.72 input / $0.72 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); Qwen2.5-VL 72B Instruct costs $2.80 input / $8.40 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.72 per million tokens for Qwen-VL OCR versus $0.75 for Aya Expanse 32B (1× as much) and $4.20 for Qwen2.5-VL 72B Instruct (5.8× 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, Qwen2.5-VL 72B Instruct 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, Qwen2.5-VL 72B Instruct 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?
Qwen2.5-VL 72B Instruct has the largest context window at 131,072 tokens, against 128,000 for Aya Expanse 32B and 34,096 for Qwen-VL OCR. Maximum output per response: Aya Expanse 32B up to 4,000, Qwen2.5-VL 72B Instruct up to 8,192, Qwen-VL OCR up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Aya Expanse 32B accepts text; Qwen2.5-VL 72B Instruct accepts text and images; Qwen-VL OCR accepts text and images. Qwen2.5-VL 72B Instruct handles the widest range of inputs.
Are any of these open source?
Aya Expanse 32B and Qwen2.5-VL 72B Instruct publishes its weights (CC-BY-NC-4.0) and can be self-hosted; 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; Qwen2.5-VL 72B Instruct came out Sep 2024. Knowledge cutoff: Qwen2.5-VL 72B Instruct 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.
