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 Large 3 2512
mistralai/mistral-large-2512Try Mistral: Mistral Large 3 2512 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 Large 3 2512 at a glance
- Input price is 11% higher than the median of 434 Text models.
- Context window of 262,144 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 $0.00437.
About Mistral: Mistral Large 3 2512
Mistral: Mistral Large 3 2512 is a text generation model from Mistral, identified on api14 by the model id mistralai/mistral-large-2512. It is Mistral's most capable model to date, built on a sparse mixture-of-experts architecture with 41B active parameters out of 675B total, and it is released under the Apache 2.0 license. The provider release date is 2025-12-01.
The model accepts text, images and files as input, and it produces text as output. Its context window is 262144 tokens, and the maximum output is 209715 tokens, so it can take in very large inputs and return long responses in a single request. Supported request parameters include frequency_penalty, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools and top_p. Because it handles images and files alongside text, it can work with mixed inputs rather than plain prompts alone.
Those capabilities point to a few practical uses. Long documents, such as contracts, research papers or codebases, fit comfortably inside the context window, so summarisation, question answering and extraction over large inputs are reasonable fits. Image and file inputs make it usable for tasks where a prompt refers to a screenshot, a diagram or an attached document. Tool calling and structured outputs suit agent style workflows and pipelines that need machine readable responses, while the seed and temperature controls help when you want reproducible or tightly constrained generation.
To call it through api14, use the OpenAI-compatible API with the model id mistralai/mistral-large-2512. Send your request to the chat completions endpoint in the usual OpenAI format, placing the model id in the model field, and pass any of the supported parameters listed above as part of the request body. No separate SDK is required if you already have an OpenAI client; point it at the api14 base URL and keep your existing request structure.
The main thing to weigh is output length against your workflow. The maximum output of 209715 tokens is generous, but if your task is short and latency sensitive, a smaller model may be a better fit. Similarly, if you only need plain text generation with no images, files or tool calls, the extra input modalities will not be used. For everything else, this model covers long context, mixed inputs and structured or tool driven output in one place.
How to call the Mistral: Mistral Large 3 2512 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-large-2512".
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-large-2512",
"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
- 262,144
- Max output
- 209,715
- Input
- text, image, file
- Output
- text
Requests on api14 · last 7 days
Mistral: Mistral Large 3 2512: frequently asked questions
- How much does the Mistral: Mistral Large 3 2512 API cost?
- Mistral: Mistral Large 3 2512 costs Input $1.75 / 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 Large 3 2512?
- Mistral: Mistral Large 3 2512 reads up to 262,144 tokens per request: prompt, history and documents together. It writes up to 209,715 output tokens per response.
- What can Mistral: Mistral Large 3 2512 do?
- Mistral: Mistral Large 3 2512 accepts text, image, file and returns text. It supports tool calling, structured JSON output.
- How do I call Mistral: Mistral Large 3 2512 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "mistralai/mistral-large-2512". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Mistral: Mistral Large 3 2512?
- Comparable Text models at a similar price: OpenAI: GPT-4.1 Mini, Perplexity: Sonar, Nous: Hermes 3 405B Instruct. Each runs through the same API key, so switching is one string.
Mistral: Mistral Large 3 2512 community
New topicThis community has no topics yet. Open the first one about Mistral: Mistral Large 3 2512.