Mistral Small 3.1 24B
VerifiedOpen multimodal model for integrated text and image tasks.
About Mistral Small 3.1 24B
Mistral Small 3.1 24B features a multimodal architecture that accepts both textual and visual inputs. Released with open weights by Mistral, it supports broad research and customization. Its 128000-token context window accommodates lengthy documents or multi-turn interactions.
The design enables joint reasoning across images and text without requiring separate pipelines. Open availability removes licensing barriers and allows fine-tuning for specialized domains. This approach delivers practical performance for cross-modal workloads.
Common uses include visual question answering, image captioning, and multimodal assistants. Teams integrate it into content analysis tools, educational platforms, and research prototypes. The model suits both individual experimentation and production deployments.
Capabilities
How Mistral Small 3.1 24B compares
Mistral Small 3.1 24B (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Mistral Small 3.1 24B ranks #24 of 124
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Multimodal document processing
Handles combined text and image inputs within its 128k token context for tasks like analyzing illustrated reports or mixed-media articles.
Long-context visual Q&A
Supports detailed question answering over extended sequences that include both textual passages and associated images.
Efficient multimodal inference
Provides balanced performance for production applications needing vision-language capabilities without excessive resource demands.
Strengths & limitations
Strengths
- +Efficient handling of combined text and image inputs
- +Strong long-context processing up to 128k tokens
- +Balanced performance for a 24B model
- +Good instruction adherence
Limitations
- –Smaller scale may limit depth on complex reasoning tasks
- –Multimodal support restricted to text and images
- –Context length capped at 128k tokens
Cost calculator
Estimate what Mistral Small 3.1 24B would cost for your usage.
Based on Mistral Small 3.1 24B's $0.35/1M input · $0.55/1M 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-small-3.1-24b-instruct",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: mistralai/mistral-small-3.1-24b-instruct
Editor's verdict
Mistral Small 3.1 24B is Mistral's open-weight multimodal with a 128K-token context window.
At $0.55 per 1M output tokens, it is very cost-efficient for its class.
As an open-weight model you can self-host it or call it through a hosted API.
Best suited to efficient handling of combined text and image inputs and strong long-context processing up to 128k tokens.
Frequently asked questions
The model supports a context window of 128000 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 multimodal worth comparing.