Mistral Small Models by MistralAI
5 models2024–2026Up to 256K ctxFrom $0.1/1M input
About
Mistral AI's small frontier model family for general-purpose chat, reasoning, and agent use cases.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
5 in view
Mistral Small 4Current
Use when the workload needs 256K context, tool use, and function calling.
2026-03256K contexttool usefunction calling
Use when the workload needs 128K context, 24B parameters, and structured outputs.
2025-12128K context24B parametersstructured outputs
Mistral Small 3.2 24BCurrent
Use when the workload needs 128K context, 24B parameters, and tool use.
2025-06128K context24B parameterstool use
Mistral Small 3Current
Use when the workload needs 33K context, tool use, and function calling.
2025-0133K contexttool usefunction calling
Mistral SmallCurrent
Use when the workload needs 32K context and structured outputs.
2024-0232K contextstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral Small 4 | Use when the workload needs 256K context, tool use, and function calling. | 2026-03 | 256K contexttool usefunction calling | Current |
| Mistral Small 3.1 24B Instruct | Use when the workload needs 128K context, 24B parameters, and structured outputs. | 2025-12 | 128K context24B parametersstructured outputs | Current |
| Mistral Small 3.2 24B | Use when the workload needs 128K context, 24B parameters, and tool use. | 2025-06 | 128K context24B parameterstool use | Current |
| Mistral Small 3 | Use when the workload needs 33K context, tool use, and function calling. | 2025-01 | 33K contexttool usefunction calling | Current |
| Mistral Small | Use when the workload needs 32K context and structured outputs. | 2024-02 | 32K contextstructured outputs | Current |
Release Timeline
5 release groups2026-03
1 current
Mistral Small 4
Current256K contexttool usefunction calling
2025-12
1 current
Mistral Small 3.1 24B Instruct
Current128K context24B parametersstructured outputs
2025-06
1 current
Mistral Small 3.2 24B
Current128K context24B parameterstool use
2025-01
1 current
Mistral Small 3
Current33K contexttool usefunction calling
2024-02
1 current
Mistral Small
Current32K contextstructured outputs
Specifications(5 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|
| Mistral Small 4 | 2026-03 | 256K | 119B (6.5B active) | Yes | Yes | Yes | Yes | No | No |
| Mistral Small 3.1 24B Instruct | 2025-12 | 128K | 24B | Yes | Yes | No | No | Yes | No |
| Mistral Small 3.2 24B | 2025-06 | 128K | 24B | Yes | Yes | Yes | Yes | Yes | Yes |
| Mistral Small 3 | 2025-01 | 33K | — | No | No | Yes | Yes | Yes | No |
| Mistral Small | 2024-02 | 32K | — | No | No | No | No | Yes | No |
Available From(9 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Mistral Small | Mistral AI Studio | $0.1 | $0.3 | Serverless |
| Mistral Small 3 | Together AI | $0.1 | $0.3 | Serverless |
| Mistral Small 3.1 24B Instruct | Together AI | $0.1 | $0.3 | Serverless |
| Mistral Small 4 | OpenRouter | $0.15 | $0.6 | Serverless |
| Mistral Small 4 | Mistral AI Studio | $0.15 | $0.6 | Serverless |
| Mistral Small 3.1 24B Instruct | OpenRouter | $0.35 | $0.56 | Serverless |
| Mistral Small 3.1 24B Instruct | Fireworks AI | $0.9 | $0.9 | Serverless |
| Mistral Small | Microsoft Foundry | $1 | $3 | Provisioned |
| Mistral Small | AWS Bedrock | $1 | $3 | Serverless |
Comparisons
- GPT-4o Mini (07-18) vs Mistral Small 3.1 24B Instruct
- Claude 3.5 Haiku vs Mistral Small 3.1 24B Instruct
- Gemini 2.5 Flash vs Mistral Small 3.1 24B Instruct
- Llama 4 Scout 17B-16E Instruct vs Mistral Small 3.1 24B Instruct
Frequently Asked Questions
- What is Mistral Small used for?
- Mistral Small is used for vision and multimodal work, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does Mistral Small compare to Ministral?
- Mistral Small by MistralAI is strongest where you need vision and multimodal work, while Ministral by MistralAI is the closest related family to check for structured outputs. Mistral Small has 5 listed variants and reaches up to 256K context, while Ministral reaches up to 32K context, so compare the specs and pricing tables before choosing a production model.
- Which Mistral Small model should I use?
- For the lowest listed input price, start with Mistral Small through Mistral AI Studio at $0.1/1M input tokens. For the most capable/latest local choice, evaluate Mistral Small 3.2 24B with 128K context and tool use, function calling, structured outputs, and multimodal inputs.
