Mistral AI
Operationalยท checked every few minutes

Ministral 3 3B API

The Ministral 3 3B API: Mistral AI's smallest open-weight model, with vision, for fast, high-volume work, 70% below Mistral's list price

Price per 1M tokens70%off
Input
$0.03$0.10
Output
$0.03$0.10
Get your API keyTry it in the playground
Model IDministral-3-3b
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-3-3b",
    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 3B 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
$0.03$0.10
Output
per 1M tokens
$0.03$0.10

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
$1.80
Mistral AI list price
$6.00
You save every month$4.20

$50.40 a year

Overview

What is Ministral 3 3B?

Ministral 3 3B is the smallest model in Mistral AI's Ministral 3 family, released on December 2, 2025: an open-weight model that reads text and images, made for fast, low-cost work such as classification, extraction, translation and image captions. The Zurelay Ministral 3 3B 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 3B pairs a 3.4B-parameter language model with a 0.4B-parameter vision encoder, and Mistral says it fits in 8GB of GPU memory at FP8. On Zurelay the model ID is ministral-3-3b, and it costs $0.03 per 1M input tokens and $0.03 per 1M output tokens.

Mistral built Ministral 3 for edge and local use, and points the 3B model at lightweight, real-time work: image captions, text classification, translation, data extraction and short content. 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 56.8 on WildBench, level with Qwen3-VL-4B-Instruct and ahead of Gemma 3 4B (49.1), and 0.830 on MATH, ahead of Gemma 3 4B (0.759) and behind Qwen3-VL-4B-Instruct (0.900). Qwen3-VL-4B-Instruct also leads it on Arena Hard, 0.438 against 0.305. 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 360 tokens a second and knew little about events after 2024, as small models tend to, so put the facts it needs in the prompt. You pay $0.03 per 1M input tokens and $0.03 per 1M output tokens against Mistral's list price of $0.10 and $0.10.

Strengths

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

01

Fast and very cheap

About 360 tokens a second in our tests, at $0.03 per 1M input tokens, for steps that run millions of times.

02

Reads images

A 0.4B-parameter vision encoder reads photos, screenshots and scans next to your text, for captions and quick visual checks.

03

Tools and JSON

Function calling and JSON output that Mistral describes as native, for routing, extraction and small agent steps.

04

Open weights

Apache 2.0 weights on Hugging Face, small enough for 8GB of GPU memory, so what you build on Zurelay carries over to a local copy later.

Use cases

  • Classification and routing

    Sort tickets, tag content and pick the next step in a pipeline, with JSON schema output for the code that follows.

  • Extraction

    Pull fields from text, forms and screenshots into JSON at a very low price per call.

  • Translation

    Quick translation between the languages Mistral lists, including English, French, Spanish, German, Chinese, Japanese and Arabic.

  • Image captions

    Short descriptions and alt text for photos and screenshots at volume.

Get started

Call Ministral 3 3B 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-3-3b

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

    ministral-3-3b

Works with the tools you already use

Compare

Similar models. All on the same key.

70%off

Ministral 3 14B

$0.06 / $0.06 per 1M tokens

Pick Ministral 3 14B, the largest Ministral 3 model, for stronger answers: 0.551 against 0.305 on Arena Hard in Mistral's tests, at twice the price per token.

Ministral 3 14B 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
90%off

DeepSeek V4.1 Flash

$0.03 / $0.12 per 1M tokens

Pick DeepSeek V4.1 Flash for a 1M-token context and thinking on harder text and image tasks.

DeepSeek V4.1 Flash API

FAQ

Ministral 3 3B API questions.

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

How much does the Ministral 3 3B API cost?

On Zurelay, ministral-3-3b costs $0.03 per 1M input tokens and $0.03 per 1M output tokens. Mistral's list price is $0.10 input and $0.10 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 3B 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-3-3b". Zurelay also accepts ministral-3-3b-instruct, mistralai/ministral-3-3b and ministral-3b. Mistral recommends a temperature of 0.1 or lower for production work.

What is the Ministral 3 3B 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 3B 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 3B: a request that includes one is turned away with a clear error before anything is billed.

Does Ministral 3 3B 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 3B Reasoning model, which Zurelay doesn't serve. For answers with thinking, use Qwen 3.8 Flash or DeepSeek V4.1 Flash.

Does Ministral 3 3B 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 3B or Ministral 3 14B?

Both read text and images, hold 131,072 tokens on Zurelay and call tools. 14B pairs a 13.5B-parameter language model with the same 0.4B vision encoder and scores higher in Mistral's tests (0.551 against 0.305 on Arena Hard, 68.5 against 56.8 on WildBench), at twice the price. 3B is faster, about 360 tokens a second against 170 in our tests, and suits simple, high-volume steps.

Is Ministral 3 3B 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 3B fits in 8GB 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 3B?

Yes. Requests for ministral-3-3b run on Mistral AI's Ministral 3 3B 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