Codestral vs Pixtral 12B vs Qwen2.5-VL 7B Instruct
Pixtral 12B comes out ahead, 64 to 51 and 48 on our weighted score, and it is the cheaper option too.
Mistral AICodestral
48/100- ECI—
- Price$0.30 / $0.90
- Context256K
- Our pickMistral AI
Pixtral 12B
64/100- ECI—
- Price$0.15 / $0.15
- Context128K
Alibaba (Qwen)Qwen2.5-VL 7B Instruct
51/100- ECI—
- Price$0.35 / $1.05
- Context131K
Pixtral 12B is our pick
Pixtral 12B is the better all-round choice, scoring 64/100 against Qwen2.5-VL 7B Instruct (51) and Codestral (48). It leads on price. Codestral wins on 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 pricePixtral 12BPixtral 12B $0.15 · Codestral $0.45 · Qwen2.5-VL 7B Instruct $0.525 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Qwen2.5-VL 7B Instruct 131,072 · Pixtral 12B 128,000 tokens
- Widest inputsPixtral 12B and Qwen2.5-VL 7B InstructCodestral: Text · Pixtral 12B: Text, Images · Qwen2.5-VL 7B Instruct: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Codestral | Pixtral 12B | Qwen2.5-VL 7B Instruct |
|---|---|---|---|---|
| Price | 50% | 66 | 89 | 63 |
| Inputs & features | 30% | 25 | 50 | 50 |
| Context window | 20% | 36 | 24 | 24 |
| Overall | 100% | 48/100 | 64/100 | 51/100 |
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 | CodestralMistral AI | Pixtral 12BMistral AI | Qwen2.5-VL 7B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.15 (best) | $0.35 |
| Output | $0.90 | $0.15 (best) | $1.05 |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 | $0.15 (best) | $0.525 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Mistral API | Official Alibaba API |
| Limits | |||
| Context window | 256,000 tokens (best) | 128,000 tokens | 131,072 tokens |
| Max output | 4,096 tokens | 128,000 tokens (best) | 8,192 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 | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | codestral-latest | pixtral-12b | qwen2-5-vl-7b-instruct |
| API providers | 3 | 4 (best) | 1 |
| Released | May 29, 2024 | Sep 1, 2024 | Sep 2024 |
| Knowledge cutoff | Oct 2024 | Sep 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.
- Codestral$4.80
- Pixtral 12B$1.80
- Qwen2.5-VL 7B Instruct$5.60
Which should you choose?
Which is better: Codestral, Pixtral 12B or Qwen2.5-VL 7B Instruct?
Pixtral 12B is the better all-round choice, scoring 64/100 against Qwen2.5-VL 7B Instruct (51) and Codestral (48). It leads on price. Codestral wins on 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, Codestral, Pixtral 12B or Qwen2.5-VL 7B Instruct?
Pixtral 12B is cheaper at $0.15 input / $0.15 output per million tokens (official Mistral API price). Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Pixtral 12B versus $0.45 for Codestral (3× as much) and $0.525 for Qwen2.5-VL 7B Instruct (3.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Pixtral 12B has not been scored yet and Qwen2.5-VL 7B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Pixtral 12B and Qwen2.5-VL 7B Instruct 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?
Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-VL 7B Instruct and 128,000 for Pixtral 12B. Maximum output per response: Codestral up to 4,096, Pixtral 12B up to 128,000, Qwen2.5-VL 7B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Pixtral 12B accepts text and images; Qwen2.5-VL 7B Instruct accepts text and images. Pixtral 12B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Pixtral 12B is the newest, released Sep 1, 2024. Qwen2.5-VL 7B Instruct came out Sep 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Pixtral 12B Sep 2024, Qwen2.5-VL 7B Instruct 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.
