# Mistral Large 3

Mistral's large general-purpose model built on a sparse mixture-of-experts foundation, activating 41B parameters per forward pass from a 675B total pool for efficient inference.

- **Model ID:** `mistral/mistral-large-3`
- **Type:** chat
- **Providers:** mistral
- **Context window:** 262,144
- **Maximum output tokens:** 256,000
- **Pricing:** $0.5/1M input tokens, $1.5/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/mistral-large-3

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

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

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

## About

Announced December 2, 2025, Mistral Large 3 marks Mistral's return to the mixture-of-experts (MoE) architecture that defined their earlier Mixtral series, now at a larger scale. With 675B total parameters and 41B active per forward pass, Mistral Large 3 represents a substantial architectural evolution from the dense models that preceded it in the Large lineage.

The sparse MoE design lets Mistral Large 3 maintain inference efficiency comparable to a smaller dense model while drawing on a large total parameter pool for complex tasks. This architecture offers a tradeoff between capability and inference cost.

Through AI Gateway, you can access Mistral Large 3 without separate Mistral API credentials. Built-in observability gives you cost and latency visibility across every request.

## What to consider

Mistral Large 3's return to MoE architecture brings sparse activation, where only part of the total parameters run per token, to Mistral's largest general-purpose open release as of the Mistral 3 announcement.

## When to use

### Best For

- Tasks demanding high capability from Mistral's general-purpose MoE lineup
- Complex reasoning and analysis tasks that benefit from a large total parameter pool
- Long-form content generation requiring coherent multi-step logic
- Applications where Mistral's ecosystem (tooling, fine-tuning, enterprise agreements) is important
- Workflows where MoE inference efficiency is preferred over pure dense-model approaches

### Consider Alternatives When

- Your task requires explicit chain-of-thought reasoning steps (consider Magistral Medium)
- Cost efficiency is the primary constraint and a smaller model meets accuracy requirements
- You need vision capabilities (consider Pixtral Large)

## Best for

- **High-capability MoE tasks:** Demanding Mistral's general-purpose MoE lineup
- **Complex reasoning and analysis:** Tasks that benefit from a large total parameter pool
- **Long-form content generation:** Long outputs where coherent multi-step logic has to hold across the whole piece
- **Mistral ecosystem fit:** Applications that rely on its tooling, fine-tuning, or enterprise agreements
- **MoE inference efficiency:** Workflows preferred over pure dense-model approaches

## Consider alternatives

- **Explicit chain-of-thought reasoning:** Your task requires reasoning traces (consider Magistral Medium)
- **Primary cost constraint:** Mistral Small or a Ministral variant meets accuracy requirements at lower per-token cost than the 675B flagship
- **Vision capabilities:** You need multimodal input (consider Pixtral Large)

## Frequently asked questions

### What is Mistral Large 3's architecture?

A sparse mixture-of-experts (MoE) model with 675B total parameters and 41B active per forward pass.

### Is this the first Mistral MoE model?

No. Mistral describes Mistral Large 3 as the company's first MoE model since the Mixtral series, returning to sparse architecture at a larger scale.

### When was Mistral Large 3 added to AI Gateway?

December 2, 2025.

### How does the MoE architecture affect inference cost?

Only 41B of 675B total parameters activate per forward pass, so inference costs stay closer to a 41B dense model than a 675B dense model.

### Does AI Gateway support BYOK for Mistral Large 3?

Yes. AI Gateway supports Bring Your Own Key (BYOK) configuration. Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

### How does Mistral Large 3 compare to Magistral Medium?

Mistral Large 3 is the general-purpose MoE model in Mistral's lineup. Magistral Medium is a reasoning model with traceable chain-of-thought and published AIME 2024 scores. Pick Magistral Medium when you need explicit reasoning traces; pick Mistral Large 3 for general tasks without that requirement.

### What observability does AI Gateway provide for Mistral Large 3?

Request-level cost, latency, token counts, and provider routing decisions, without additional instrumentation.

## Links

- [Model page](https://vercel.com/ai-gateway/models/mistral-large-3)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://mistral.ai/news/mistral-3)
- [Provider pricing](https://mistral.ai/pricing#api-pricing)