Codestral vs Qwen2.5-VL 7B Instruct vs solar-mini
Too close to call on our weighted score (solar-mini 52, Qwen2.5-VL 7B Instruct 51, Codestral 48). The right pick depends on what you value most.
Mistral AICodestral
48/100- ECI—
- Price$0.30 / $0.90
- Context256K
Alibaba (Qwen)Qwen2.5-VL 7B Instruct
51/100- ECI—
- Price$0.35 / $1.05
- Context131K
Upstage
solar-mini
52/100- ECI—
- Price$0.15 / $0.15
- Context33K
Too close to call
It is close. Our weighted score puts them within a point (solar-mini 52/100, Qwen2.5-VL 7B Instruct 51/100, Codestral 48/100), so choose by what matters most for your work: solar-mini on price and Codestral for long inputs. 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 pricesolar-minisolar-mini $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 · solar-mini 32,768 tokens
- Widest inputsQwen2.5-VL 7B InstructCodestral: Text · Qwen2.5-VL 7B Instruct: Text, Images · solar-mini: Text
- Self-hostingCodestral and Qwen2.5-VL 7B InstructPublishes downloadable weights
| Measure | Weight | Codestral | Qwen2.5-VL 7B Instruct | solar-mini |
|---|---|---|---|---|
| Price | 50% | 66 | 63 | 89 |
| Inputs & features | 30% | 25 | 50 | 25 |
| Context window | 20% | 36 | 24 | 0 |
| Overall | 100% | 48/100 | 51/100 | 52/100 |
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 | Qwen2.5-VL 7B InstructAlibaba (Qwen) | solar-miniUpstage |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.35 | $0.15 (best) |
| Output | $0.90 | $1.05 | $0.15 (best) |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 | $0.525 | $0.15 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Alibaba API | Official Upstage API |
| Limits | |||
| Context window | 256,000 tokens (best) | 131,072 tokens | 32,768 tokens |
| Max output | 4,096 tokens | 8,192 tokens (best) | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| 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 | Proprietary |
| API model ID | codestral-latest | qwen2-5-vl-7b-instruct | solar-mini |
| API providers | 3 (best) | 1 | 1 |
| Released | May 29, 2024 | Sep 2024 | Jun 12, 2024 |
| Knowledge cutoff | Oct 2024 | Apr 2024 | Sep 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
- Qwen2.5-VL 7B Instruct$5.60
- solar-mini$1.80
Which should you choose?
Which is better: Codestral, Qwen2.5-VL 7B Instruct or solar-mini?
It is close. Our weighted score puts them within a point (solar-mini 52/100, Qwen2.5-VL 7B Instruct 51/100, Codestral 48/100), so choose by what matters most for your work: solar-mini on price and Codestral for long inputs. 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, Qwen2.5-VL 7B Instruct or solar-mini?
solar-mini is cheaper at $0.15 input / $0.15 output per million tokens (official Upstage 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 solar-mini 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, Qwen2.5-VL 7B Instruct has not been scored yet and solar-mini has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Qwen2.5-VL 7B Instruct and solar-mini 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 32,768 for solar-mini. Maximum output per response: Codestral up to 4,096, Qwen2.5-VL 7B Instruct up to 8,192, solar-mini up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Qwen2.5-VL 7B Instruct accepts text and images; solar-mini accepts text. Qwen2.5-VL 7B Instruct handles the widest range of inputs.
Are any of these open source?
Codestral and Qwen2.5-VL 7B Instruct publishes its weights and can be self-hosted; solar-mini is proprietary.
Which is newer?
Qwen2.5-VL 7B Instruct is the newest, released Sep 2024. solar-mini came out Jun 12, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Qwen2.5-VL 7B Instruct Apr 2024, solar-mini Sep 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.
