Qwen Plus vs Vision Small vs Codestral
Vision Small comes out ahead, 61 to 54 and 49 on our weighted score, though Codestral is 3.5× cheaper per token.
Alibaba (Qwen)Qwen Plus
54/100- ECI—
- Price$0.40 / $1.20
- Context1M
- Our pick
VisparkVision Small
61/100- ECI—
- Price$1.05 / $3.16
- Context1M
Mistral AICodestral
49/100- ECI—
- Price$0.30 / $0.90
- Context256K
Vision Small is our pick
Vision Small is the better all-round choice, scoring 61/100 against Qwen Plus (54) and Codestral (49). It leads on inputs & features. Codestral wins on price. 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 priceCodestralCodestral $0.45 · Qwen Plus $0.60 · Vision Small $1.58 per 1M tokens (3:1 blend)
- Longest contextQwen Plus and Vision SmallQwen Plus 1,000,000 · Vision Small 1,000,000 · Codestral 256,000 tokens
- Widest inputsVision SmallQwen Plus: Text · Vision Small: Text, Images, PDFs, Audio, Video · Codestral: Text
- Self-hostingCodestralPublishes downloadable weights
| Measure | Weight | Qwen Plus | Vision Small | Codestral |
|---|---|---|---|---|
| Price | 50% | 58 | 39 | 64 |
| Inputs & features | 30% | 45 | 100 | 35 |
| Context window | 20% | 60 | 60 | 36 |
| Overall | 100% | 54/100 | 61/100 | 49/100 |
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 | Qwen PlusAlibaba (Qwen) | Vision SmallVispark | CodestralMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 | $1.05 | $0.30 (best) |
| Output | $1.20 | $3.16 | $0.90 (best) |
| Cached input | $0.08 | — | $0.03 (best) |
| Blended (3:1) | $0.60 | $1.58 | $0.45 (best) |
| Long-context rate | Over 256K: $1.20 / $3.60 | Same rate | Same rate |
| Price source | Official Alibaba API | Official Vispark API | Official Mistral API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 1,000,000 tokens (best) | 256,000 tokens |
| Max output | 32,768 tokens | 65,536 tokens (best) | 4,096 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 | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | qwen-plus | vispark/vision-small | codestral-latest |
| API providers | 10 (best) | 1 | 4 |
| Released | Jan 25, 2024 | May 15, 2024 | May 29, 2024 |
| Knowledge cutoff | Apr 2024 | — | Oct 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen Plus$6.40
- Vision Small$16.82
- Codestral$4.80
Which should you choose?
Which is better: Qwen Plus, Vision Small or Codestral?
Vision Small is the better all-round choice, scoring 61/100 against Qwen Plus (54) and Codestral (49). It leads on inputs & features. Codestral wins on price. 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, Qwen Plus, Vision Small or Codestral?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen Plus costs $0.40 input / $1.20 output per million tokens (official Alibaba 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 $0.45 per million tokens for Codestral versus $0.60 for Qwen Plus (1.3× as much) and $1.58 for Vision Small (3.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen Plus has not been scored yet, Vision Small has not been scored yet and Codestral has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen Plus, Vision Small and Codestral yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Qwen Plus and Vision Small have the largest context windows (1,000,000 and 1,000,000 tokens), against 256,000 for Codestral. Maximum output per response: Qwen Plus up to 32,768, Vision Small up to 65,536, Codestral up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Qwen Plus accepts text; Vision Small accepts text, images, PDFs, audio and video; Codestral accepts text. Vision Small handles the widest range of inputs.
Are any of these open source?
Codestral publishes its weights and can be self-hosted; Qwen Plus and Vision Small is proprietary.
Which is newer?
Codestral is the newest, released May 29, 2024. Vision Small came out May 15, 2024; Qwen Plus came out Jan 25, 2024. Knowledge cutoff: Qwen Plus Apr 2024, Codestral Oct 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.
