Model comparison
Magistral 1.1 (Small & Medium) vs Magistral 1.0 (Small & Medium)
- 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
- Input
- $0.50 / 1M tokens (Magistral Small); $2.00 / 1M tokens (Magistral Medium)
- Output
- $1.50 / 1M tokens (Magistral Small); $5.00 / 1M tokens (Magistral Medium)
- Context
- 128K
- Released
- 2025-06-10
Magistral 1.0 (Small & Medium) is cheaper on input tokens ($0.5 vs $2 per 1M, 4×).
Specs and pricing side by side
| Spec | Magistral 1.1 (Small & Medium) | Magistral 1.0 (Small & Medium) |
|---|---|---|
| Maker | Mistral AI | Mistral AIsame |
| Released | 2025-07-24 | 2025-06-10 |
| Context window | 128K (Small) / 40K (Medium) | 128K |
| Max output | 40K recommended | Not separately published; recommended working… |
| Input price | $2.00 / 1M tokens (Medium); $0.50 / 1M (Small) | $0.50 / 1M tokens (Magistral Small); $2.00 / 1M tokens (Magistral Medium) |
| Output price | $5.00 / 1M tokens (Medium); $1.50 / 1M (Small) | $1.50 / 1M tokens (Magistral Small); $5.00 / 1M tokens (Magistral Medium) |
| Parameters | 24B (Small); Medium undisclosed | Magistral Small: 24B (≈23.6B). Magistral Medium: undisclosed (built on Mistral Medium 3). |
| License | Apache 2.0 (Small) / Mistral commercial, API-only (Medium) | Magistral Small: Apache 2.0 (open weights). Magistral Medium: proprietary, API-only. |
| Weights | Open weights | Open weightssame |
| Modalities | Text | Textsame |
| Knowledge cutoff | Not disclosed | Not disclosed by Mistral. |
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 1.1 (Small & Medium), Magistral 1.0 (Small & Medium).
Which one should you pick?
Pick Magistral 1.1 (Small & Medium) if…
- Your use case is: math, science, and logic problems that benefit from explicit multi-step reasoning.
Pick Magistral 1.0 (Small & Medium) if…
- Cost matters: input tokens cost 4× less ($0.5 vs $2 per 1M).
- Your use case is: self-hosted, privacy-sensitive reasoning workloads using the open-weight Magistral Small.
FAQ
Which is better, Magistral 1.1 (Small & Medium) or Magistral 1.0 (Small & Medium)?
Magistral 1.0 (Small & Medium) is cheaper on input tokens ($0.5 vs $2 per 1M, 4×). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Magistral 1.0 (Small & Medium)?
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. Magistral 1.0 (Small & Medium): $0.50 / 1M tokens (Magistral Small); $2.00 / 1M tokens (Magistral Medium) input, $1.50 / 1M tokens (Magistral Small); $5.00 / 1M tokens (Magistral Medium) output (list API prices as published by each maker).
What are the context windows of Magistral 1.1 (Small & Medium) and Magistral 1.0 (Small & Medium)?
Magistral 1.1 (Small & Medium) offers 128K (Small) / 40K (Medium) with up to 40K recommended output; Magistral 1.0 (Small & Medium) offers 128K with up to Not separately published; recommended working window is 40K tokens (performance may degrade beyond that, within the 128K maximum). output.
Is Magistral 1.1 (Small & Medium) newer than Magistral 1.0 (Small & Medium)?
Magistral 1.1 (Small & Medium) was released 2025-07-24; Magistral 1.0 (Small & Medium) was released 2025-06-10.