Mistral AI
Operationeel· elke paar minuten gecontroleerd

Ministral 3 14B API

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

Prijs per 1M tokens70%korting
Input
$0.06$0.20
Output
$0.06$0.20
Haal je API-sleutel opProbeer het in de 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="")

Basis-URL https://api.zurelay.com/v1. Werkt met elke OpenAI SDK. Chat API-documentatie

Contextvenster
128K tokens
Redeneren
Geen
Input
Text, Image
Uitgebracht
2 dec 2025
Status
Operationeel

Prijzen

Prijzen van de Ministral 3 14B API. Een fractie van de catalogusprijs.

Je betaalt naar gebruik vanuit je prepaidtegoed, zonder abonnement. Opwaarderen kan vanaf $10. Mislukte verzoeken worden nooit in rekening gebracht.

TariefZurelayCatalogusprijs Mistral AI
Input
per 1M tokens
$0.06$0.20
Output
per 1M tokens
$0.06$0.20

Eén tarief voor elke promptlengte, up to the full 128K context window. Streaming, toolaanroepen en gestructureerde uitvoer kosten niets extra.

Besparing berekenen

Stel de schuifregelaars in op je maandelijkse verbruik.

Invoertokens per maand50M
Uitvoertokens per maand10M
Zurelay
$3.60
Catalogusprijs Mistral AI
$12.00
Je bespaart elke maand$8.40

$100.80 per jaar

Overzicht

Wat 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 en 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, voor 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 en 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 kost $0.06 per 1M input tokens and $0.06 per 1M outputtokens.

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

Sterke punten

Waar Ministral 3 14B in uitblinkt. En wat teams ermee bouwen.

01

Strong for its size

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

02

Leest afbeeldingen

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

03

Tools en JSON

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

04

Open gewichten

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

Toepassingen

  • Assistants en chat

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

  • Agent steps

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

  • Extraction from text and afbeeldingen

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

  • Multilingual work

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

Aan de slag

Roep Ministral 3 14B aan in drie stappen.

Geen wachtlijst en geen nieuwe SDK. Als je code al met OpenAI werkt, werkt die ook met Zurelay.

  1. 1

    Sleutel aanmaken

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

    Haal je API-sleutel op
  2. 2

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

    ministral-3-14b

Werkt met de tools die je al gebruikt

Vergelijken

Vergelijkbare modellen. Allemaal met dezelfde sleutel.

70%korting

Ministral 3 3B

$0.03 / $0.03 per 1M tokens

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

Ministral 3 3B API
53%korting

Qwen 3.8 Flash

$0.07 / $0.22 per 1M tokens

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

Qwen 3.8 Flash API
61%korting

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 en audio, video and PDF input.

Gemini 3.1 Flash-Lite API

Veelgestelde vragen

Vragen over de Ministral 3 14B API.

Nog vragen? Vraag het ons team en we antwoorden per e-mail.

Wat kost de Ministral 3 14B API?

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

Hoe roep ik the Ministral 3 14B API aan met de OpenAI SDK?

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

Wat 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 en images en writes text.

Can Ministral 3 14B read afbeeldings or PDFs?

It reads afbeeldings: send them in image_url parts, as https links or base64 data URLs, en 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 en there are no reasoning tokens tot 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 en 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, en tool_choice "none" works. Tool call ids must be at least 9 characters long, as the model's own en 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 en images, hold 131,072 tokens on Zurelay en 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 en changes. Mistral publishes base, instruct en 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, en 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, en 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.

Meer modellen op Zurelay

Alle modellen

Betaal niet langer de volle prijs.
Begin vandaag met besparen.

Maak in een paar seconden een sleutel aan, stel de SDK die je al gebruikt in op Zurelay en betaal vanaf de eerste token tot 90% minder voor elk verzoek.

Haal je API-sleutel opPraat met een engineer