Vision Small vs Codestral-22B-v0.1 vs Qwen Max
Vision Small comes out ahead, 84 to 21 and 0 on our weighted score, and it is the cheaper option too.
- Our pick
VisparkVision Small
84/100- ECI—
- Price$1.05 / $3.16
- Context1M
Mistral AICodestral-22B-v0.1
0/100- ECI—
- Price—
- Context33K
Alibaba (Qwen)Qwen Max
21/100- ECI—
- Price$1.60 / $6.40
- Context33K
Vision Small is our pick
Vision Small is the better all-round choice, scoring 84/100 against Qwen Max (21) and Codestral-22B-v0.1 (0). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. 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 priceVision SmallVision Small $1.58 · Qwen Max $2.80 per 1M tokens (3:1 blend) · Codestral-22B-v0.1 unpriced
- Longest contextVision SmallVision Small 1,000,000 · Codestral-22B-v0.1 32,768 · Qwen Max 32,768 tokens
- Widest inputsVision SmallVision Small: Text, Images, PDFs, Audio, Video · Codestral-22B-v0.1: Text · Qwen Max: Text
- Self-hostingCodestral-22B-v0.1Publishes downloadable weights (Mistral AI Non-Production License)
| Measure | Weight | Vision Small | Codestral-22B-v0.1 | Qwen Max |
|---|---|---|---|---|
| Inputs & features | 60% | 100 | 0 | 35 |
| Context window | 40% | 60 | 0 | 0 |
| Overall | 100% | 84/100 | 0/100 | 21/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Vision SmallVispark | Codestral-22B-v0.1Mistral AI | Qwen MaxAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.05 (best) | — | $1.60 |
| Output | $3.16 (best) | — | $6.40 |
| Cached input | — | — | — |
| Blended (3:1) | $1.58 (best) | — | $2.80 |
| Long-context rate | Same rate | — | Same rate |
| Price source | Official Vispark API | — | Official Alibaba API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 32,768 tokens | 32,768 tokens |
| Max output | 65,536 tokens (best) | 8,192 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Proprietary | OpenMistral AI Non-Production License | Proprietary |
| API model ID | vispark/vision-small | — | qwen-max |
| API providers | 1 | — | 8 (best) |
| Released | May 15, 2024 | May 29, 2024 | Apr 3, 2024 |
| Knowledge cutoff | — | — | 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.
- Vision Small$16.82
- Codestral-22B-v0.1—
- Qwen Max$28.80
Which should you choose?
Which is better: Vision Small, Codestral-22B-v0.1 or Qwen Max?
Vision Small is the better all-round choice, scoring 84/100 against Qwen Max (21) and Codestral-22B-v0.1 (0). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Vision Small, Codestral-22B-v0.1 or Qwen Max?
Vision Small is cheaper at $1.05 input / $3.16 output per million tokens (official Vispark API price). Qwen Max costs $1.60 input / $6.40 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $1.58 per million tokens for Vision Small versus $2.80 for Qwen Max (1.8× as much). Codestral-22B-v0.1 has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Vision Small has not been scored yet, Codestral-22B-v0.1 has not been scored yet and Qwen Max has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Vision Small, Codestral-22B-v0.1 and Qwen Max yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Codestral-22B-v0.1 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 32,768 for Codestral-22B-v0.1 and 32,768 for Qwen Max. Maximum output per response: Vision Small up to 65,536, Codestral-22B-v0.1 up to 8,192, Qwen Max up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Vision Small accepts text, images, PDFs, audio and video; Codestral-22B-v0.1 accepts text; Qwen Max accepts text. Vision Small handles the widest range of inputs.
Are any of these open source?
Codestral-22B-v0.1 publishes its weights (Mistral AI Non-Production License) and can be self-hosted; Vision Small and Qwen Max is proprietary.
Which is newer?
Codestral-22B-v0.1 is the newest, released May 29, 2024. Vision Small came out May 15, 2024; Qwen Max came out Apr 3, 2024. Knowledge cutoff: Qwen Max 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 Nov 2, 2026.
