Magistral Medium vs Qwen-MT Plus vs Step 1 (32K)
Magistral Medium comes out ahead, 30 to 18 and 12 on our weighted score, and it is the cheaper option too.
- Our pick
Mistral AIMagistral Medium
30/100- ECI—
- Price$2.00 / $5.00
- Context128K
Alibaba (Qwen)Qwen-MT Plus
12/100- ECI—
- Price$2.46 / $7.37
- Context16K
StepFunStep 1 (32K)
18/100- ECI—
- Price$2.05 / $9.59
- Context33K
Magistral Medium is our pick
Magistral Medium is the better all-round choice, scoring 30/100 against Step 1 (32K) (18) and Qwen-MT Plus (12). It leads on price, inputs & features 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 priceMagistral MediumMagistral Medium $2.75 · Qwen-MT Plus $3.69 · Step 1 (32K) $3.94 per 1M tokens (3:1 blend)
- Longest contextMagistral MediumMagistral Medium 128,000 · Step 1 (32K) 32,768 · Qwen-MT Plus 16,384 tokens
- Widest inputsSame inputsMagistral Medium: Text · Qwen-MT Plus: Text · Step 1 (32K): Text
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Magistral Medium | Qwen-MT Plus | Step 1 (32K) |
|---|---|---|---|---|
| Price | 50% | 29 | 23 | 22 |
| Inputs & features | 30% | 35 | 0 | 25 |
| Context window | 20% | 24 | 0 | 0 |
| Overall | 100% | 30/100 | 12/100 | 18/100 |
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 | Magistral MediumMistral AI | Qwen-MT PlusAlibaba (Qwen) | Step 1 (32K)StepFun |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.00 (best) | $2.46 | $2.05 |
| Output | $5.00 (best) | $7.37 | $9.59 |
| Cached input | — | — | $0.41 |
| Blended (3:1) | $2.75 (best) | $3.69 | $3.94 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Alibaba API | Official StepFun (Global) API |
| Limits | |||
| Context window | 128,000 tokens (best) | 16,384 tokens | 32,768 tokens |
| Max output | 16,384 tokens | 8,192 tokens | 32,768 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | magistral-medium-latest | qwen-mt-plus | step-1-32k |
| API providers | 4 (best) | 1 | 1 |
| Released | Mar 17, 2025 | Jan 2025 | Jan 1, 2025 |
| Knowledge cutoff | Jun 2025 | Apr 2024 | Jun 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Magistral Medium$30.00
- Qwen-MT Plus$39.34
- Step 1 (32K)$39.68
Which should you choose?
Which is better: Magistral Medium, Qwen-MT Plus or Step 1 (32K)?
Magistral Medium is the better all-round choice, scoring 30/100 against Step 1 (32K) (18) and Qwen-MT Plus (12). It leads on price, inputs & features 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, Magistral Medium, Qwen-MT Plus or Step 1 (32K)?
Magistral Medium is cheaper at $2.00 input / $5.00 output per million tokens (official Mistral API price). 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 $2.75 per million tokens for Magistral Medium versus $3.69 for Qwen-MT Plus (1.3× as much) and $3.94 for Step 1 (32K) (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Magistral Medium has not been scored yet, Qwen-MT Plus has not been scored yet and Step 1 (32K) has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Magistral Medium, Qwen-MT Plus and Step 1 (32K) 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?
Magistral Medium has the largest context window at 128,000 tokens, against 32,768 for Step 1 (32K) and 16,384 for Qwen-MT Plus. Maximum output per response: Magistral Medium up to 16,384, Qwen-MT Plus up to 8,192, Step 1 (32K) up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Magistral Medium accepts text; Qwen-MT Plus accepts text; Step 1 (32K) accepts text. They handle the same number of input types.
Are any of these open source?
No. Magistral Medium, Qwen-MT Plus and Step 1 (32K) are proprietary and only available through APIs and apps.
Which is newer?
Magistral Medium is the newest, released Mar 17, 2025. Qwen-MT Plus came out Jan 2025; Step 1 (32K) came out Jan 1, 2025. Knowledge cutoff: Magistral Medium Jun 2025, Qwen-MT Plus Apr 2024, Step 1 (32K) Jun 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.
