Qwen2.5-VL 72B Instruct vs Vision Small vs Aion-RP 1.0 (8B)
Vision Small comes out ahead, 61 to 44 and 24 on our weighted score, though Qwen2.5-VL 72B Instruct is 41% cheaper per token.
Alibaba (Qwen)Qwen2.5-VL 72B Instruct
44/100- ECI—
- Price$0.905 / $1.00
- Context131K
- Our pick
VisparkVision Small
61/100- ECI—
- Price$1.05 / $3.16
- Context1M
Aion Labs
Aion-RP 1.0 (8B)
24/100- ECI—
- Price$0.80 / $1.60
- Context33K
Vision Small is our pick
Vision Small is the better all-round choice, scoring 61/100 against Qwen2.5-VL 72B Instruct (44) and Aion-RP 1.0 (8B) (24). 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-VL 72B InstructQwen2.5-VL 72B Instruct $0.93 · Aion-RP 1.0 (8B) $1.00 · Vision Small $1.58 per 1M tokens (3:1 blend)
- Longest contextVision SmallVision Small 1,000,000 · Qwen2.5-VL 72B Instruct 131,072 · Aion-RP 1.0 (8B) 32,768 tokens
- Widest inputsVision SmallQwen2.5-VL 72B Instruct: Text, Images · Vision Small: Text, Images, PDFs, Audio, Video · Aion-RP 1.0 (8B): Text
- Self-hostingQwen2.5-VL 72B Instruct and Aion-RP 1.0 (8B)Publishes downloadable weights
| Measure | Weight | Qwen2.5-VL 72B Instruct | Vision Small | Aion-RP 1.0 (8B) |
|---|---|---|---|---|
| Price | 50% | 49 | 39 | 48 |
| Inputs & features | 30% | 50 | 100 | 0 |
| Context window | 20% | 25 | 60 | 0 |
| Overall | 100% | 44/100 | 61/100 | 24/100 |
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 | Qwen2.5-VL 72B InstructAlibaba (Qwen) | Vision SmallVispark | Aion-RP 1.0 (8B)Aion Labs |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.905 | $1.05 | $0.80 (best) |
| Output | $1.00 (best) | $3.16 | $1.60 |
| Cached input | — | — | — |
| Blended (3:1) | $0.93 (best) | $1.58 | $1.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 6 providers | Official Vispark API | Median of 4 providers |
| Limits | |||
| Context window | 131,072 tokens | 1,000,000 tokens (best) | 32,768 tokens |
| Max output | 8,192 tokens | 65,536 tokens (best) | 29,491 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | — | vispark/vision-small | — |
| API providers | 6 (best) | 1 | 4 |
| Released | Jan 26, 2025 | May 15, 2024 | Feb 4, 2025 |
| Knowledge cutoff | Apr 2024 | — | Dec 31, 2023 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen2.5-VL 72B Instruct$11.06
- Vision Small$16.82
- Aion-RP 1.0 (8B)$11.20
Which should you choose?
Which is better: Qwen2.5-VL 72B Instruct, Vision Small or Aion-RP 1.0 (8B)?
Vision Small is the better all-round choice, scoring 61/100 against Qwen2.5-VL 72B Instruct (44) and Aion-RP 1.0 (8B) (24). 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, Qwen2.5-VL 72B Instruct, Vision Small or Aion-RP 1.0 (8B)?
Qwen2.5-VL 72B Instruct is cheaper at $0.905 input / $1.00 output per million tokens (median across 6 API providers). Aion-RP 1.0 (8B) costs $0.80 input / $1.60 output per million tokens (median across 4 API providers); 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 $0.93 per million tokens for Qwen2.5-VL 72B Instruct versus $1.00 for Aion-RP 1.0 (8B) (1.1× as much) and $1.58 for Vision Small (1.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen2.5-VL 72B Instruct has not been scored yet, Vision Small has not been scored yet and Aion-RP 1.0 (8B) has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen2.5-VL 72B Instruct, Vision Small and Aion-RP 1.0 (8B) yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aion-RP 1.0 (8B) 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-VL 72B Instruct and 32,768 for Aion-RP 1.0 (8B). Maximum output per response: Qwen2.5-VL 72B Instruct up to 8,192, Vision Small up to 65,536, Aion-RP 1.0 (8B) up to 29,491 tokens.
Which can read images, PDFs, audio or video?
Qwen2.5-VL 72B Instruct accepts text and images; Vision Small accepts text, images, PDFs, audio and video; Aion-RP 1.0 (8B) accepts text. Vision Small handles the widest range of inputs.
Are any of these open source?
Qwen2.5-VL 72B Instruct and Aion-RP 1.0 (8B) publishes its weights and can be self-hosted; Vision Small is proprietary.
Which is newer?
Aion-RP 1.0 (8B) is the newest, released Feb 4, 2025. Qwen2.5-VL 72B Instruct came out Jan 26, 2025; Vision Small came out May 15, 2024. Knowledge cutoff: Qwen2.5-VL 72B Instruct Apr 2024, Aion-RP 1.0 (8B) Dec 31, 2023.
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.
