Mistral AI
Operationalยท checked every few minutes

Ministral 3 14B API

The Ministral 3 14B API: the largest Ministral 3 model, with vision and tool calling, 70% below Mistral's list price

Price per 1M tokens70%off
Input
$0.06$0.20
Output
$0.06$0.20
Get your API keyTry it in the playground
Model IDministral-3-14b
chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="ministral-3-14b",
    messages=[{"role": "user", "content": "Explain quicksort in two sentences."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK. Chat API docs

Context window
128K tokens
Reasoning
None
Input
Text, Image
Released
Dec 2, 2025
Status
Operational

Pricing

Ministral 3 14B API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

RateZurelayMistral AI list
Input
per 1M tokens
$0.06$0.20
Output
per 1M tokens
$0.06$0.20

One rate at every prompt length, up to the full 128K context window. Streaming, tool calls and structured outputs cost nothing extra.

Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M
Output tokens per month10M
Zurelay
$3.60
Mistral AI list price
$12.00
You save every month$8.40

$100.80 a year

Overview

What is Ministral 3 14B?

Ministral 3 14B is the largest model in Mistral AI's Ministral 3 family, released on December 2, 2025: an open-weight model that reads text and images and, by Mistral's account, performs comparably to its larger Mistral Small 3.2 24B. The Zurelay Ministral 3 14B API serves its instruct version through one OpenAI-compatible endpoint with a 131,072-token context window, at 70% below Mistral's list price.

Mistral AI released the Ministral 3 family on December 2, 2025, alongside Mistral Large 3, in three sizes: 3B, 8B and 14B. Each size comes as a base, an instruct and a reasoning model, all with image understanding and all under the Apache 2.0 license, with the weights on Hugging Face. Ministral 3 14B pairs a 13.5B-parameter language model with a 0.4B-parameter vision encoder, and Mistral says it fits in 24GB of GPU memory at FP8. On Zurelay the model ID is ministral-3-14b, and it costs $0.06 per 1M input tokens and $0.06 per 1M output tokens.

Mistral built Ministral 3 for edge and local use, and points the 14B model at private chat and assistant deployments on limited hardware, local agents and fine-tuning. It handles dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean and Arabic. Mistral says its Ministral instruct models often write an order of magnitude fewer tokens than comparable models.

On Mistral's model card the instruct model scores 0.551 on Arena Hard, 68.5 on WildBench and 0.904 on MATH, ahead of Qwen3 14B without thinking (0.427, 65.1 and 0.870) and Gemma 3 12B (0.436, 63.2 and 0.854). On MM MTBench, a multimodal chat test, it scores 8.49 against 6.70 for Gemma 3 12B. These are Mistral's numbers, not independent ones.

The instruct model answers directly without reasoning first, so reasoning_effort has no effect. It calls tools, several at once and while streaming, and returns JSON for json_object or json_schema in response_format. Mistral lists a 256K context window on its own API; on Zurelay a request holds up to 131,072 tokens. In our tests it wrote about 170 tokens a second and knew little about events after 2024, so put the facts it needs in the prompt. You pay $0.06 per 1M input tokens and $0.06 per 1M output tokens against Mistral's list price of $0.20 and $0.20.

Strengths

Where Ministral 3 14B shines. And what teams build with it.

01

Strong for its size

0.551 on Arena Hard and 68.5 on WildBench in Mistral's tests, ahead of Qwen3 14B and Gemma 3 12B, and comparable to Mistral Small 3.2 24B by Mistral's account.

02

Reads images

8.49 on MM MTBench in Mistral's tests. Send screenshots, charts and photos next to your text.

03

Tools and JSON

Calls several tools at once, also while streaming, and follows a JSON schema, for agent steps and extraction.

04

Open weights

Apache 2.0 weights on Hugging Face that fit in 24GB of GPU memory at FP8, so what you build on Zurelay carries over to a self-hosted copy later.

Use cases

  • Assistants and chat

    Customer-facing chat and internal assistants that need good everyday answers at a very low price per token.

  • Agent steps

    Tool-calling steps such as looking things up, filling forms and choosing the next action, with JSON for the code that follows.

  • Extraction from text and images

    Pull fields from emails, documents and screenshots into a JSON schema.

  • Multilingual work

    Translate, summarize and answer in the languages Mistral lists, from French and German to Chinese, Japanese and Arabic.

Get started

Call Ministral 3 14B in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

  1. 1

    Create a key

    Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.

    Get your API key
  2. 2

    Point your SDK at Zurelay

    Change the base URL. Everything else in your code stays the same.

    https://api.zurelay.com/v1
  3. 3

    Use ministral-3-14b

    Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.

    ministral-3-14b

Works with the tools you already use

Compare

Similar models. All on the same key.

70%off

Ministral 3 3B

$0.03 / $0.03 per 1M tokens

Pick Ministral 3 3B for the simplest, highest-volume steps at half the price per token, about twice as fast in our tests.

Ministral 3 3B API
53%off

Qwen 3.8 Flash

$0.07 / $0.22 per 1M tokens

Pick Qwen 3.8 Flash for a 1M-token context, video input and a thinking mode when a task needs more than a small model.

Qwen 3.8 Flash API
61%off

Gemini 3.1 Flash-Lite

$0.10 / $0.59 per 1M tokens

Pick Gemini 3.1 Flash-Lite for Google's low-cost model with a 1M-token context and audio, video and PDF input.

Gemini 3.1 Flash-Lite API

FAQ

Ministral 3 14B API questions.

Anything else? Ask our team and weโ€™ll answer by email.

How much does the Ministral 3 14B API cost?

On Zurelay, ministral-3-14b costs $0.06 per 1M input tokens and $0.06 per 1M output tokens. Mistral's list price is $0.20 input and $0.20 output per 1M, so you save 70%. One rate applies at every prompt length, and failed requests are never billed.

How do I call the Ministral 3 14B API with the OpenAI SDK?

Install the official openai package, set base_url to https://api.zurelay.com/v1 and use your Zurelay API key. Then send a Chat Completions request with model set to "ministral-3-14b". Zurelay also accepts ministral-3-14b-instruct, mistralai/ministral-3-14b and ministral-14b. Mistral recommends a temperature of 0.1 or lower for production work.

What is the Ministral 3 14B context window?

On Zurelay a request holds up to 131,072 tokens. Mistral lists a 256K window on its own API. The model reads text and images and writes text.

Can Ministral 3 14B read images or PDFs?

It reads images: send them in image_url parts, as https links or base64 data URLs, and they count as input tokens. Mistral suggests images close to square, with very wide or thin ones cropped. Zurelay doesn't take PDFs, audio or video for Ministral 3 14B: a request that includes one is turned away with a clear error before anything is billed.

Does Ministral 3 14B reason before it answers?

No. Zurelay serves the instruct model, which answers directly, so reasoning_effort has no effect and there are no reasoning tokens to pay for. Mistral also publishes a separate Ministral 3 14B Reasoning model, which Zurelay doesn't serve. For answers with thinking, use Qwen 3.8 Flash or DeepSeek V4.1 Flash.

Does Ministral 3 14B support tool calling and JSON output?

Yes. Pass tools as you would to any OpenAI model; it can call several at once, also while streaming. A tool forced by name is called, and tool_choice "none" works. Tool call ids must be at least 9 characters long, as the model's own and OpenAI's are. For JSON, send response_format with json_object or json_schema and the answer comes back as JSON.

Should I use Ministral 3 14B or Ministral 3 3B?

Both read text and images, hold 131,072 tokens on Zurelay and call tools. 14B is the stronger model, with a 13.5B-parameter language model against 3.4B, and scores higher in Mistral's tests: 0.551 against 0.305 on Arena Hard and 68.5 against 56.8 on WildBench. 3B costs half as much and was about twice as fast in our tests, so it suits the simplest, highest-volume steps.

Is Ministral 3 14B open source?

Its weights are open under the Apache 2.0 license, which allows commercial use and changes. Mistral publishes base, instruct and reasoning versions on Hugging Face and says the 14B fits in 24GB of GPU memory at FP8. The API is the quick way to use it without running your own hardware.

Is this the real Ministral 3 14B?

Yes. Requests for ministral-3-14b run on Mistral AI's Ministral 3 14B Instruct, and Zurelay doesn't swap in a different model. Only smart routing, which you turn on yourself, can answer with a close alternative when the model is down, and the x-zurelay-model header names the model that answered. Responses are sampled, so wording varies between runs. Zurelay is independent and is not affiliated with or endorsed by Mistral AI.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer