# Ministral 3B

Less than half the size of Mistral 7B, Ministral 3B delivers faster inference and higher scores on most benchmarks. Ministral 3B targets high-frequency API workloads where cost compounds fast.

- **Model ID:** `mistral/ministral-3b`
- **Type:** chat
- **Providers:** mistral
- **Context window:** 131,072
- **Maximum output tokens:** 4,000
- **Pricing:** $0.1/1M input tokens, $0.1/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/ministral-3b

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'mistral/ministral-3b',
  prompt: 'Why is the sky blue?'
})
```

## About

Mistral released Ministral 3B on October 16, 2024 as the most compact member of the Ministral edge family. Ministral 3B outperforms the older Mistral 7B, a model more than twice its parameter count, on most evaluation categories. Mistral attributes this to architectural refinements specific to the Ministral generation.

Ministral 3B ships with a context window of 131.1K tokens and supports function calling out of the box. That combination makes it a practical lightweight tool-dispatch agent in multi-step pipelines where a larger model would be wasteful for structured routing work.

Production use falls under the Mistral Commercial License.

## What to consider

Symmetrical input/output pricing simplifies cost estimation. You don't need to model prompt-to-completion ratios separately.

## When to use

### Best For

- Lightweight function-calling agents that dispatch tools in multi-step workflows
- High-frequency classification, summarization, or knowledge retrieval at minimal cost
- Cost-sensitive production APIs processing millions of requests

### Consider Alternatives When

- You need the memory-efficient sliding-window attention that Ministral 8B provides for long-context tasks
- Complex reasoning or code generation is required
- Your workload involves image understanding (consider Ministral 14B)

## Best for

- **Lightweight function-calling agents:** Agents that dispatch tools in multi-step workflows at minimal cost
- **High-frequency classification:** Summarization or knowledge retrieval at minimal cost
- **Cost-sensitive production APIs:** Services processing millions of requests where per-call cost dominates

## Consider alternatives

- **Long-context memory efficiency:** You need the sliding-window attention Ministral 8B provides
- **Complex reasoning or code generation:** These workloads exceed the 3B capability
- **Image understanding:** Your workload involves vision (consider Ministral 14B)

## Frequently asked questions

### How can Ministral 3B outperform the larger Mistral 7B?

Mistral credits architectural refinements in the Ministral generation.

### What types of tasks is Ministral 3B well suited for?

Structured function calling, classification, simple summarization, and knowledge retrieval. Use Ministral 3B as a lightweight dispatch layer in agentic systems where the work is routing, not deep reasoning.

### What context length does Ministral 3B support?

131.1K tokens.

### What licensing options are available?

The Mistral Commercial License covers production use.

## Links

- [Model page](https://vercel.com/ai-gateway/models/ministral-3b)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://mistral.ai/news/ministraux/)
- [Provider pricing](https://docs.mistral.ai/platform/pricing/)