Codestral vs Phi-4-mini vs Qwen2.5-VL 7B Instruct
Phi-4-mini comes out ahead, 58 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 pick
MicrosoftPhi-4-mini
58/100- ECI—
- Price$0.075 / $0.30
- Context128K
Alibaba (Qwen)Qwen2.5-VL 7B Instruct
51/100- ECI—
- Price$0.35 / $1.05
- Context131K
Phi-4-mini is our pick
Phi-4-mini is the better all-round choice, scoring 58/100 against Qwen2.5-VL 7B Instruct (51) and Codestral (48). It leads on price. Codestral wins on context window. Qwen2.5-VL 7B Instruct wins on inputs & features. 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 pricePhi-4-miniPhi-4-mini $0.131 · 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 · Phi-4-mini 128,000 tokens
- Widest inputsQwen2.5-VL 7B InstructCodestral: Text · Phi-4-mini: Text · 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 | Phi-4-mini | Qwen2.5-VL 7B Instruct |
|---|---|---|---|---|
| Price | 50% | 66 | 92 | 63 |
| Inputs & features | 30% | 25 | 25 | 50 |
| Context window | 20% | 36 | 24 | 24 |
| Overall | 100% | 48/100 | 58/100 | 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 | Phi-4-miniMicrosoft | Qwen2.5-VL 7B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.075 (best) | $0.35 |
| Output | $0.90 | $0.30 (best) | $1.05 |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 | $0.131 (best) | $0.525 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Azure API | Official Alibaba API |
| Limits | |||
| Context window | 256,000 tokens (best) | 128,000 tokens | 131,072 tokens |
| Max output | 4,096 tokens | 4,096 tokens | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | 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 | phi-4-mini | qwen2-5-vl-7b-instruct |
| API providers | 3 (best) | 1 | 1 |
| Released | May 29, 2024 | Dec 11, 2024 | Sep 2024 |
| Knowledge cutoff | Oct 2024 | Oct 2023 | 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
- Phi-4-mini$1.35
- Qwen2.5-VL 7B Instruct$5.60
Which should you choose?
Which is better: Codestral, Phi-4-mini or Qwen2.5-VL 7B Instruct?
Phi-4-mini is the better all-round choice, scoring 58/100 against Qwen2.5-VL 7B Instruct (51) and Codestral (48). It leads on price. Codestral wins on context window. Qwen2.5-VL 7B Instruct wins on inputs & features. 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, Phi-4-mini or Qwen2.5-VL 7B Instruct?
Phi-4-mini is cheaper at $0.075 input / $0.30 output per million tokens (official Azure 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 $0.131 per million tokens for Phi-4-mini versus $0.45 for Codestral (3.4× as much) and $0.525 for Qwen2.5-VL 7B Instruct (4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Phi-4-mini 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, Phi-4-mini 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 Phi-4-mini. Maximum output per response: Codestral up to 4,096, Phi-4-mini up to 4,096, Qwen2.5-VL 7B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Phi-4-mini accepts text; Qwen2.5-VL 7B Instruct accepts text and images. Qwen2.5-VL 7B Instruct 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?
Phi-4-mini is the newest, released Dec 11, 2024. Qwen2.5-VL 7B Instruct came out Sep 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Phi-4-mini Oct 2023, 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.
