Step 1 (32K) vs Ministral 8B Instruct vs Qwen-MT Plus
Ministral 8B Instruct comes out ahead, 57 to 18 and 12 on our weighted score, and it is the cheaper option too.
StepFunStep 1 (32K)
18/100- ECI—
- Price$2.05 / $9.59
- Context33K
- Our pick
Mistral AIMinistral 8B Instruct
57/100- ECI—
- Price$0.15 / $0.15
- Context131K
Alibaba (Qwen)Qwen-MT Plus
12/100- ECI—
- Price$2.46 / $7.37
- Context16K
Ministral 8B Instruct is our pick
Ministral 8B Instruct is the better all-round choice, scoring 57/100 against Step 1 (32K) (18) and Qwen-MT Plus (12). It leads on price and 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 priceMinistral 8B InstructMinistral 8B Instruct $0.15 · Qwen-MT Plus $3.69 · Step 1 (32K) $3.94 per 1M tokens (3:1 blend)
- Longest contextMinistral 8B InstructMinistral 8B Instruct 131,072 · Step 1 (32K) 32,768 · Qwen-MT Plus 16,384 tokens
- Widest inputsSame inputsStep 1 (32K): Text · Ministral 8B Instruct: Text · Qwen-MT Plus: Text
- Self-hostingMinistral 8B InstructPublishes downloadable weights (Mistral Research License)
| Measure | Weight | Step 1 (32K) | Ministral 8B Instruct | Qwen-MT Plus |
|---|---|---|---|---|
| Price | 50% | 22 | 89 | 23 |
| Inputs & features | 30% | 25 | 25 | 0 |
| Context window | 20% | 0 | 24 | 0 |
| Overall | 100% | 18/100 | 57/100 | 12/100 |
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 | Step 1 (32K)StepFun | Ministral 8B InstructMistral AI | Qwen-MT PlusAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| GPQA DiamondGraduate-level science questions | — | 27.2% | — |
| Price per million tokens | |||
| Input | $2.05 | $0.15 (best) | $2.46 |
| Output | $9.59 | $0.15 (best) | $7.37 |
| Cached input | $0.41 | — | — |
| Blended (3:1) | $3.94 | $0.15 (best) | $3.69 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official StepFun (Global) API | Median of 1 providers | Official Alibaba API |
| Limits | |||
| Context window | 32,768 tokens | 131,072 tokens (best) | 16,384 tokens |
| Max output | 32,768 tokens (best) | 8,192 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenMistral Research License | Proprietary |
| API model ID | step-1-32k | — | qwen-mt-plus |
| API providers | 1 | 1 | 1 |
| Released | Jan 1, 2025 | Oct 16, 2024 | Jan 2025 |
| Knowledge cutoff | Jun 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.
- Step 1 (32K)$39.68
- Ministral 8B Instruct$1.80
- Qwen-MT Plus$39.34
Which should you choose?
Which is better: Step 1 (32K), Ministral 8B Instruct or Qwen-MT Plus?
Ministral 8B Instruct is the better all-round choice, scoring 57/100 against Step 1 (32K) (18) and Qwen-MT Plus (12). It leads on price and 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, Step 1 (32K), Ministral 8B Instruct or Qwen-MT Plus?
Ministral 8B Instruct is cheaper at $0.15 input / $0.15 output per million tokens (median across 1 API provider). Qwen-MT Plus costs $2.46 input / $7.37 output per million tokens (official Alibaba API price); Step 1 (32K) costs $2.05 input / $9.59 output per million tokens (official StepFun (Global) API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 8B Instruct versus $3.69 for Qwen-MT Plus (25× as much) and $3.94 for Step 1 (32K) (26× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Step 1 (32K) has not been scored yet, Ministral 8B Instruct has not been scored yet and Qwen-MT Plus has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Step 1 (32K), Ministral 8B Instruct and Qwen-MT Plus yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen-MT Plus does not support tool calling, which most coding agents need.
Which has the bigger context window?
Ministral 8B Instruct has the largest context window at 131,072 tokens, against 32,768 for Step 1 (32K) and 16,384 for Qwen-MT Plus. Maximum output per response: Step 1 (32K) up to 32,768, Ministral 8B Instruct up to 8,192, Qwen-MT Plus up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Step 1 (32K) accepts text; Ministral 8B Instruct accepts text; Qwen-MT Plus accepts text. They handle the same number of input types.
Are any of these open source?
Ministral 8B Instruct publishes its weights (Mistral Research License) and can be self-hosted; Step 1 (32K) and Qwen-MT Plus is proprietary.
Which is newer?
Step 1 (32K) is the newest, released Jan 1, 2025. Qwen-MT Plus came out Jan 2025; Ministral 8B Instruct came out Oct 16, 2024. Knowledge cutoff: Step 1 (32K) Jun 2024, Qwen-MT Plus 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.
