Mistral AI
Opérationnel· vérifié toutes les quelques minutes

Ministral 3 14B API

Tarif public The Ministral 3 14B API: the largest Ministral 3 model, with vision et tool calling, 70% below Mistral's

Prix par 1M tokens70%de réduction
Entrée
$0.06$0.20
Sortie
$0.06$0.20
Obtenez votre clé APIEssayez dans l’espace de test
Identifiant du modèleministral-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="")

URL de base https://api.zurelay.com/v1. Compatible avec tous les SDK OpenAI. Documentation de l’API de chat

Fenêtre de contexte
128K tokens
Raisonnement
Aucun
Entrée
Text, Image
Date de sortie
2 déc. 2025
Statut
Opérationnel

Tarifs

Tarifs de l’API Ministral 3 14B. Une fraction du prix catalogue.

Payez à l’usage avec votre crédit prépayé, sans abonnement. Rechargez dès $10. Les requêtes qui échouent ne sont jamais facturées.

TarifZurelayTarif public Mistral AI
Entrée
par 1M tokens
$0.06$0.20
Sortie
par 1M tokens
$0.06$0.20

Un tarif unique, quelle que soit la longueur du prompt, up to the full 128K context window. Le streaming, les appels d’outils et les sorties structurées sont sans supplément.

Simulateur d’économies

Ajustez les curseurs selon votre utilisation mensuelle.

Tokens d’entrée par mois50M
Tokens de sortie par mois10M
Zurelay
$3.60
Tarif public Mistral AI
$12.00
Vos économies chaque mois$8.40

$100.80 par an

Vue d’ensemble

Qu’est-ce que 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 et 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, en 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 et 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 coûte $0.06 per 1M input tokens and $0.06 par 1M tokens en sortie.

Mistral built Ministral 3 for edge et local use, et 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 et 0.904 on MATH, ahead of Qwen3 14B without thinking (0.427, 65.1 et 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 et while streaming, et 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.

Points forts

Là où Ministral 3 14B excelle. Et ce que les équipes créent avec.

01

Strong for its size

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

02

Lecture d’images

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

03

Outils et JSON

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

04

Poids ouverts

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

Cas d’usage

  • Assistants et chat

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

  • Agent steps

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

  • Images Extraction from text and

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

  • Multilingual work

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

Commencer

Appelez Ministral 3 14B en trois étapes.

Pas de liste d’attente ni de nouveau SDK. Si votre code communique déjà avec OpenAI, il peut aussi communiquer avec Zurelay.

  1. 1

    Créer une clé

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

    Obtenez votre clé API
  2. 2

    Point your SDK en 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 et usage reporting work as you expect.

    ministral-3-14b

Compatible avec les outils que vous utilisez déjà

Comparer

Modèles similaires. Tous avec la même clé.

70%de réduction

Ministral 3 3B

$0.03 / $0.03 par 1M tokens

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

API Ministral 3 3B
53%de réduction

Qwen 3.8 Flash

$0.07 / $0.22 par 1M tokens

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

API Qwen 3.8 Flash
61%de réduction

Gemini 3.1 Flash-Lite

$0.10 / $0.59 par 1M tokens

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

API Gemini 3.1 Flash-Lite

FAQ

Questions sur l’API Ministral 3 14B.

D’autres questions ? Contactez notre équipe et nous vous répondrons par e-mail.

Combien coûte l’API Ministral 3 14B ?

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

Comment appeler the Ministral 3 14B API avec le SDK OpenAI ?

Install the official openai package, set base_url to https://api.zurelay.com/v1 et 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 et ministral-14b. Mistral recommends a temperature of 0.1 or lower for production work.

Qu’est-ce que 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 et images et 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, et 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 et there are no reasoning tokens à 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 et 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, et tool_choice "none" works. Tool call ids must be at least 9 characters long, as the model's own et 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 et images, hold 131,072 tokens on Zurelay et 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 et changes. Mistral publishes base, instruct et 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, et 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, et 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.

D’autres modèles sur Zurelay

Tous les modèles

Ne payez plus le prix catalogue.
Économisez dès aujourd’hui.

Créez une clé en quelques secondes, configurez votre SDK habituel pour utiliser Zurelay et payez chaque requête jusqu’à 90% moins cher, dès le premier token.

Obtenez votre clé APIParler à un ingénieur