Mistral Medium 3.1
VerifiedOpen-weight multimodal model for text, image, and file tasks.
About Mistral Medium 3.1
Mistral Medium 3.1 combines multimodal input handling with an extensive context capacity. Its open-weight release allows researchers and developers to inspect and modify the model architecture. This design targets applications requiring integrated analysis of documents, visuals, and lengthy text sequences.
Strengths include native support for mixed-modality inputs without external preprocessing pipelines. The model maintains coherence across large contexts, making it suitable for tasks that span multiple data types. Users benefit from the transparency of open weights for fine-tuning on domain-specific datasets.
Typical usage involves building applications for document understanding, visual question answering, and multi-file reasoning workflows. Developers integrate it into systems that require both image interpretation and extended textual context. Its flexibility suits research environments and production deployments alike.
Capabilities
How Mistral Medium 3.1 compares
Mistral Medium 3.1 (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Mistral Medium 3.1 ranks #55 of 122
Nova 2 LiteSources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Multimodal Document Analysis
The model processes documents containing text and images together, delivering reasoned insights from combined visual and textual data.
Long-Context Code Projects
It manages extensive codebases within its 131072-token context window while generating code and adhering to detailed instructions.
Image and File Reasoning Workflows
Users upload images or files for analysis, enabling tasks that require multimodal reasoning and structured output generation.
Strengths & limitations
Strengths
- +Effective integration of text and visual inputs
- +Handles large documents and extended conversations
- +Versatile across general reasoning and coding tasks
Limitations
- –Medium-tier model may lag behind larger variants on complex problems
- –No native support for audio or video modalities
- –File handling limited to supported formats
Cost calculator
Estimate what Mistral Medium 3.1 would cost for your usage.
Based on Mistral Medium 3.1's $0.40/1M input · $2.00/1M 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-medium-3.1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: mistralai/mistral-medium-3.1
Editor's verdict
Mistral Medium 3.1 is Mistral's proprietary multimodal with a 131K-token context window.
At $2.00 per 1M output tokens, it is mid-priced for its class.
It is available through Mistral's API and aggregators like OpenRouter.
Best suited to effective integration of text and visual inputs and handles large documents and extended conversations.
Frequently asked questions
The model provides a context window of 131072 tokens for handling long inputs and conversations.
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 multimodal worth comparing.