Model comparison
Magistral 1.2 (Small & Medium) vs Magistral 1.1 (Small & Medium)
- Input
- $2.00 / 1M tokens (Magistral Medium); $0.50 / 1M tokens (Magistral Small)
- Output
- $5.00 / 1M tokens (Magistral Medium); $1.50 / 1M tokens (Magistral Small)
- Context
- 128K
- Released
- 2025-09-17
- Input
- $2.00 / 1M tokens (Medium); $0.50 / 1M (Small)
- Output
- $5.00 / 1M tokens (Medium); $1.50 / 1M (Small)
- Context
- 128K (Small) / 40K (Medium)
- Released
- 2025-07-24
Both charge the same $2 per 1M input tokens.
Specs and pricing side by side
| Spec | Magistral 1.2 (Small & Medium) | Magistral 1.1 (Small & Medium) |
|---|---|---|
| Maker | Mistral AI | Mistral AIsame |
| Released | 2025-09-17 | 2025-07-24 |
| Context window | 128K | 128K (Small) / 40K (Medium) |
| Max output | 128K (shared context budget; no separate… | 40K recommended |
| Input price | $2.00 / 1M tokens (Magistral Medium); $0.50 / 1M tokens (Magistral Small) | $2.00 / 1M tokens (Medium); $0.50 / 1M (Small) |
| Output price | $5.00 / 1M tokens (Magistral Medium); $1.50 / 1M tokens (Magistral Small) | $5.00 / 1M tokens (Medium); $1.50 / 1M (Small) |
| Parameters | 24B (Magistral Small 1.2); undisclosed (Magistral Medium 1.2) | 24B (Small); Medium undisclosed |
| License | Apache 2.0 (Magistral Small 1.2); proprietary (Magistral Medium 1.2) | Apache 2.0 (Small) / Mistral commercial, API-only (Medium) |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision | Text |
| Knowledge cutoff | not published | Not disclosed |
Benchmarks both models report
These two models have no benchmark in common in our registry, so there is no like-for-like score to compare. See each model’s own results: Magistral 1.2 (Small & Medium), Magistral 1.1 (Small & Medium).
Which one should you pick?
Pick Magistral 1.2 (Small & Medium) if…
- You need Vision input, which Magistral 1.1 (Small & Medium) lacks.
- Your use case is: multi-step math, logic, and STEM problem solving where a visible reasoning trace is valuable.
Pick Magistral 1.1 (Small & Medium) if…
- Your use case is: math, science, and logic problems that benefit from explicit multi-step reasoning.
FAQ
Which is better, Magistral 1.2 (Small & Medium) or Magistral 1.1 (Small & Medium)?
Both charge the same $2 per 1M input tokens. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How do Magistral 1.2 (Small & Medium) and Magistral 1.1 (Small & Medium) pricing compare?
Magistral 1.2 (Small & Medium): $2.00 / 1M tokens (Magistral Medium); $0.50 / 1M tokens (Magistral Small) input, $5.00 / 1M tokens (Magistral Medium); $1.50 / 1M tokens (Magistral Small) output. Magistral 1.1 (Small & Medium): $2.00 / 1M tokens (Medium); $0.50 / 1M (Small) input, $5.00 / 1M tokens (Medium); $1.50 / 1M (Small) output (list API prices as published by each maker).
What are the context windows of Magistral 1.2 (Small & Medium) and Magistral 1.1 (Small & Medium)?
Magistral 1.2 (Small & Medium) offers 128K with up to 128K (shared context budget; no separate output cap published) output; Magistral 1.1 (Small & Medium) offers 128K (Small) / 40K (Medium) with up to 40K recommended output.
Is Magistral 1.2 (Small & Medium) newer than Magistral 1.1 (Small & Medium)?
Magistral 1.2 (Small & Medium) was released 2025-09-17; Magistral 1.1 (Small & Medium) was released 2025-07-24.