Aya Expanse 32B vs Vision Small vs Qwen2.5-Coder-32B-Instruct
Vision Small comes out ahead, 61 to 39 and 32 on our weighted score, though Qwen2.5-Coder-32B-Instruct is 2.1× cheaper per token.
CohereAya Expanse 32B
32/100- ECI—
- Price$0.50 / $1.50
- Context128K
- Our pick
VisparkVision Small
61/100- ECI—
- Price$1.05 / $3.16
- Context1M
Alibaba (Qwen)Qwen2.5-Coder-32B-Instruct
39/100- ECI—
- Price$0.66 / $1.00
- Context131K
Vision Small is our pick
Vision Small is the better all-round choice, scoring 61/100 against Qwen2.5-Coder-32B-Instruct (39) and Aya Expanse 32B (32). It leads on inputs & features and 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 priceQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct $0.745 · Aya Expanse 32B $0.75 · Vision Small $1.58 per 1M tokens (3:1 blend)
- Longest contextVision SmallVision Small 1,000,000 · Qwen2.5-Coder-32B-Instruct 131,072 · Aya Expanse 32B 128,000 tokens
- Widest inputsVision SmallAya Expanse 32B: Text · Vision Small: Text, Images, PDFs, Audio, Video · Qwen2.5-Coder-32B-Instruct: Text
- Self-hostingAya Expanse 32B and Qwen2.5-Coder-32B-InstructPublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Aya Expanse 32B | Vision Small | Qwen2.5-Coder-32B-Instruct |
|---|---|---|---|---|
| Price | 50% | 53 | 39 | 54 |
| Inputs & features | 30% | 0 | 100 | 25 |
| Context window | 20% | 24 | 60 | 25 |
| Overall | 100% | 32/100 | 61/100 | 39/100 |
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 | Vision SmallVispark | Qwen2.5-Coder-32B-InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.50 (best) | $1.05 | $0.66 |
| Output | $1.50 | $3.16 | $1.00 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.75 | $1.58 | $0.745 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Official Vispark API | Median of 7 providers |
| Limits | |||
| Context window | 128,000 tokens | 1,000,000 tokens (best) | 131,072 tokens |
| Max output | 4,000 tokens | 65,536 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | No | Yes | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenCC-BY-NC-4.0 | Proprietary | Open |
| API model ID | c4ai-aya-expanse-32b | vispark/vision-small | — |
| API providers | 2 | 1 | 7 (best) |
| Released | Oct 24, 2024 | May 15, 2024 | Nov 12, 2024 |
| Knowledge cutoff | — | — | — |
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
- Vision Small$16.82
- Qwen2.5-Coder-32B-Instruct$8.60
Which should you choose?
Which is better: Aya Expanse 32B, Vision Small or Qwen2.5-Coder-32B-Instruct?
Vision Small is the better all-round choice, scoring 61/100 against Qwen2.5-Coder-32B-Instruct (39) and Aya Expanse 32B (32). It leads on inputs & features and 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, Aya Expanse 32B, Vision Small or Qwen2.5-Coder-32B-Instruct?
Qwen2.5-Coder-32B-Instruct is cheaper at $0.66 input / $1.00 output per million tokens (median across 7 API providers). Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price); Vision Small costs $1.05 input / $3.16 output per million tokens (official Vispark API price). At a typical mix of three input tokens to one output token, that is $0.745 per million tokens for Qwen2.5-Coder-32B-Instruct versus $0.75 for Aya Expanse 32B (1× as much) and $1.58 for Vision Small (2.1× 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, Vision Small has not been scored yet and Qwen2.5-Coder-32B-Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aya Expanse 32B, Vision Small and Qwen2.5-Coder-32B-Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Vision Small has the largest context window at 1,000,000 tokens, against 131,072 for Qwen2.5-Coder-32B-Instruct and 128,000 for Aya Expanse 32B. Maximum output per response: Aya Expanse 32B up to 4,000, Vision Small up to 65,536, Qwen2.5-Coder-32B-Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Aya Expanse 32B accepts text; Vision Small accepts text, images, PDFs, audio and video; Qwen2.5-Coder-32B-Instruct accepts text. Vision Small handles the widest range of inputs.
Are any of these open source?
Aya Expanse 32B and Qwen2.5-Coder-32B-Instruct publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Vision Small is proprietary.
Which is newer?
Qwen2.5-Coder-32B-Instruct is the newest, released Nov 12, 2024. Aya Expanse 32B came out Oct 24, 2024; Vision Small came out May 15, 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 Nov 2, 2026.
