Magistral Models by MistralAI
2 models2025Up to 128k ctxFrom $0.5/1M input
About
Magistral is a family of 2 AI models by MistralAI, released in 2025.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
2 in view
Magistral Small 2506Current
Use when the workload needs reasoning, 128k context, and 24B parameters.
2025-06reasoning128k context24B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral Magistral Small 2509 | Use when the workload needs 24B parameters. | 2025-09 | 24B parameters | Current |
| Magistral Small 2506 | Use when the workload needs reasoning, 128k context, and 24B parameters. | 2025-06 | reasoning128k context24B parameters | Current |
Release Timeline
2 release groups2025-09
1 current
Mistral Magistral Small 2509
Current24B parameters
2025-06
1 current
Magistral Small 2506
Currentreasoning128k context24B parameters
Specifications(2 models)
| Model | Released | Context | Parameters | Reasoning |
|---|---|---|---|---|
| Mistral Magistral Small 2509 | 2025-09 | — | 24B | No |
| Magistral Small 2506 | 2025-06 | 128k | 24B | Yes |
Available From(3 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Mistral Magistral Small 2509 | AWS Bedrock | $0.5 | $1.5 | Serverless |
| Mistral Magistral Small 2509 | Vercel AI Gateway | $0.5 | $1.5 | Serverless |
Frequently Asked Questions
- What is Magistral used for?
- Magistral is used for reasoning. The family description and listed model capabilities point to those workloads as the best fit.
- How does Magistral compare to Ministral?
- Magistral by MistralAI is strongest where you need reasoning, while Ministral by MistralAI is the closest related family to check for structured outputs. Magistral has 2 listed variants and reaches up to 128k context, while Ministral reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
- Which Magistral model should I use?
- For the lowest listed input price, start with Mistral Magistral Small 2509 through AWS Bedrock at $0.5/1M input tokens. For the most capable/latest local choice, evaluate Magistral Small 2506 with 128k context and reasoning.
