We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Mistral: Mistral Medium 3.1 (batch)
mistralai/mistral-medium-3.1:batchTry Mistral: Mistral Medium 3.1 (batch) now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Mistral: Mistral Medium 3.1 (batch) at a glance
- Input price is 56% lower than the median of 434 Text models.
- Context window of 131,072 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.00245.
About Mistral: Mistral Medium 3.1 (batch)
Mistral Medium 3.1 (batch) is a text generation model from Mistral, an updated version of Mistral Medium 3. Mistral describes the base model as a high-performance, enterprise-grade language model that aims to deliver frontier-level capabilities at reduced operational cost. On api14 the model is exposed under the id mistralai/mistral-medium-3.1:batch, and the batch suffix indicates the batch variant of the model. The provider release date is 2025-08-13, and the knowledge cutoff is 2025-06-30.
The model accepts text, images and files as input, and it produces text as output. It has a context window of 131,072 tokens and a maximum output of 104,857 tokens, so it can take in long documents and still return substantial responses in a single call. Supported request parameters include temperature, top_p, max_tokens, stop, seed, frequency_penalty, presence_penalty, response_format, structured_outputs, tools and tool_choice. The combination of image and file inputs with tool calling makes it suitable for tasks that mix reading material with actions.
Practical use cases follow from those capabilities. Because it reads text, images and files, it can summarize or extract information from mixed documents such as reports with embedded charts, scanned pages or spreadsheets. Its long context suits long-form analysis, multi-document comparison and codebase review. Tool calling and structured outputs make it a reasonable choice for agents and pipelines that need to call functions or return JSON that downstream code can parse. The seed parameter helps when you want repeatable sampling during testing, and stop sequences help control where generation ends.
To call it through api14, use the OpenAI-compatible chat completions endpoint with the model id mistralai/mistral-medium-3.1:batch. Because the API is OpenAI-compatible, existing OpenAI SDKs and clients work with only a base URL and key change. You can pass the supported parameters listed above in the request body, including temperature, top_p, max_tokens, stop, seed, frequency_penalty, presence_penalty, response_format, structured_outputs, tools and tool_choice. The page shows a live price table, so check there for current rates.
One limit to keep in mind is that the model outputs text only, so it cannot generate images or audio. If your task requires those output types, a different model fits better. The batch variant is also worth considering carefully: if you need immediate interactive responses rather than batched processing, check whether the non-batch version of the same model is available on api14.
How to call the Mistral: Mistral Medium 3.1 (batch) API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "mistralai/mistral-medium-3.1:batch".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "mistralai/mistral-medium-3.1:batch",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_pSpecifications
- Context length
- 131,072
- Max output
- 104,857
- Input
- text, image, file
- Output
- text
- Knowledge cutoff
- 2025-06-30
Requests on api14 · last 7 days
Mistral: Mistral Medium 3.1 (batch): frequently asked questions
- How much does the Mistral: Mistral Medium 3.1 (batch) API cost?
- Mistral: Mistral Medium 3.1 (batch) costs Input $0.70 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Mistral: Mistral Medium 3.1 (batch)?
- Mistral: Mistral Medium 3.1 (batch) reads up to 131,072 tokens per request: prompt, history and documents together. It writes up to 104,857 output tokens per response.
- What can Mistral: Mistral Medium 3.1 (batch) do?
- Mistral: Mistral Medium 3.1 (batch) accepts text, image, file and returns text. It supports tool calling, structured JSON output.
- How do I call Mistral: Mistral Medium 3.1 (batch) from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "mistralai/mistral-medium-3.1:batch". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Mistral: Mistral Medium 3.1 (batch)?
- Comparable Text models at a similar price: Z.ai: GLM 4.6V, DeepSeek: DeepSeek V3.1, Mistral: Codestral 2508. Each runs through the same API key, so switching is one string.
Mistral: Mistral Medium 3.1 (batch) community
New topicThis community has no topics yet. Open the first one about Mistral: Mistral Medium 3.1 (batch).