Mistral Medium Models by MistralAI
4 models2023–2026Up to 256K ctxFrom $0.4/1M input
About
Mistral AI's medium-sized flagship family for higher-quality general-purpose reasoning and tool use.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view
Mistral Medium 3.5Current
Use when the workload needs 256K context, 128B parameters, and reasoning.
2026-04256K context128B parametersreasoning
Mistral Medium 3Current
Use when the workload needs 128K context, tool use, and function calling.
2025-05128K contexttool usefunction calling
Mistral MediumCurrent
Use when the workload needs 32K context and structured outputs.
2023-1232K contextstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral Medium 3.5 | Use when the workload needs 256K context, 128B parameters, and reasoning. | 2026-04 | 256K context128B parametersreasoning | Current |
| Mistral Medium 3 Instruct | Use when the workload needs 128K context. | 2025-10 | 128K context | Current |
| Mistral Medium 3 | Use when the workload needs 128K context, tool use, and function calling. | 2025-05 | 128K contexttool usefunction calling | Current |
| Mistral Medium | Use when the workload needs 32K context and structured outputs. | 2023-12 | 32K contextstructured outputs | Current |
Release Timeline
4 release groups2026-04
1 current
Mistral Medium 3.5
Current256K context128B parametersreasoning
2025-10
1 current
Mistral Medium 3 Instruct
Current128K context
2025-05
1 current
Mistral Medium 3
Current128K contexttool usefunction calling
2023-12
1 current
Mistral Medium
Current32K contextstructured outputs
Specifications(4 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|---|
| Mistral Medium 3.5 | 2026-04 | 256K | 128B | Yes | Yes | Yes | Yes | Yes | Yes | No |
| Mistral Medium 3 Instruct | 2025-10 | 128K | — | No | No | No | No | No | No | No |
| Mistral Medium 3 | 2025-05 | 128K | — | Yes | Yes | No | Yes | Yes | Yes | Yes |
| Mistral Medium | 2023-12 | 32K | — | No | No | No | No | No | Yes | No |
Available From(3 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Mistral Medium | OpenRouter | $0.4 | $2 | Serverless |
| Mistral Medium 3 Instruct | Mistral AI Studio | $0.4 | $2 | Serverless |
| Mistral Medium | Mistral AI Studio | $1.5 | $7.5 | Serverless |
| Mistral Medium 3.5 | Mistral AI Studio | $1.5 | $7.5 | Serverless |
| Mistral Medium 3.5 | OpenRouter | $1.5 | $7.5 | Serverless |
Frequently Asked Questions
- What is Mistral Medium used for?
- Mistral Medium is used for vision and multimodal work, reasoning, and agent workflows and tool use. The family description and listed model capabilities point to those workloads as the best fit.
- How does Mistral Medium compare to Ministral?
- Mistral Medium 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 Medium has 4 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 Medium model should I use?
- For the lowest listed input price, start with Mistral Medium 3 Instruct through Mistral AI Studio at $0.4/1M input tokens. For the most capable/latest local choice, evaluate Mistral Medium 3.5 with 256K context and reasoning, tool use, function calling, structured outputs, and multimodal inputs.
