Mistral Large 2407
VerifiedMistral Large 2407 offers open-weight multimodal capabilities for text and file tasks.
About Mistral Large 2407
Mistral Large 2407 was designed as an open-weight multimodal system. It handles both plain text and file uploads in a single context of 131072 tokens. The architecture prioritizes broad input compatibility without closed-source restrictions.
Its open release enables fine-tuning and on-premise use by researchers and developers. This approach supports customization for specialized domains while retaining core multimodal processing strengths. Extended context handling aids tasks that require retaining large amounts of information across documents.
Typical applications include document analysis, code review with attached files, and multi-turn reasoning over mixed text and data sources. Users integrate the model into pipelines needing both language generation and file interpretation without external API dependencies.
Capabilities
Benchmarks & performance
Independent evaluation scores and measured speed.
Source: Artificial Analysis
How Mistral Large 2407 compares
Mistral Large 2407 (striped bar) vs other language models on intelligence, speed and price.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Mistral Large 2407 ranks #53 of 67
Price
USD per 1M output tokens · Lower is better · Mistral Large 2407 ranks #130 of 141
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long-Document Legal Review
The model processes extensive contracts and regulatory filings within its 131072-token context window to identify inconsistencies and extract key clauses.
Multilingual Codebase Migration
It generates and refactors code across languages while following detailed migration instructions and maintaining project structure.
Research Paper Synthesis
Users can upload multiple academic documents for summarization and cross-referencing using long-context reasoning and synthesis capabilities.
Strengths & limitations
Strengths
- +Strong reasoning on extended inputs
- +Competitive coding and technical performance
- +Efficient handling of large documents
- +Balanced speed and capability
Limitations
- –Text and file modalities only
- –No native vision or audio support
- –Standard LLM knowledge cutoff
Cost calculator
Estimate what Mistral Large 2407 would cost for your usage.
Based on Mistral Large 2407's $2.00/1M input · $6.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "mistralai/mistral-large-2407",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: mistralai/mistral-large-2407
Editor's verdict
Mistral Large 2407 is Mistral's proprietary language models with a 131K-token context window.
On independent testing it scores 13 on the Artificial Analysis Intelligence Index.
At $6.00 per 1M output tokens, it is premium-priced for its class.
It is available through Mistral's API and aggregators like OpenRouter.
Best suited to strong reasoning on extended inputs and competitive coding and technical performance.
Frequently asked questions
The model supports a context window of 131072 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Mistral models
Sibling versions in the Mistral family from Mistral.
Similar models
Other language models worth comparing.