Home
LLMs
Ministral 3 14B

Ministral 3 14B

The largest of the Ministral 3 family, a 14B dense model (13.5B language model plus a 0.4B vision encoder) under Apache 2.0, built for local and edge deployment.

Params: 13.9B
Context: 256K tokens
Released: Dec 2025
License: Apache 2.0

Visit Mistral Compare vs other LLMs →

Hosted API price

List price via Mistral · per 1M tokens

USD

Input: $0.20 /1M
Output: $0.20 /1M
Hosted by: 2 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Ministral 3 14B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Ministral 3 14B, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Mistral Creator	$0.20	$0.20	$2.40	Visit website
DigitalOcean	$0.20	$0.20	$2.40	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Ministral 3 14B needs about 12 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 1× RTX 4060 Ti at about $86 a month.

That costs the same as roughly 432M tokens a month on Mistral's API. Self-hosting is more expensive below that volume.

Fits on 1 Single node ≤ 8

What it costs to self-host Ministral 3 14B at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 256K context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	12 GB31 GB	1× RTX 4060 Ti	$86$346	432M tokens /mo2B tokens /mo
8-bit FP8 / INT8	21 GB37 GB	2× RTX 3060	$101$346	504M tokens /mo2B tokens /mo
16-bit FP16 / BF16	35 GB72 GB	4× RTX 3060	$202$403	1B tokens /mo2B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Ministral 3 14B by blended rate, each at its own cheapest provider.

Models priced nearest Ministral 3 14B per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Ministral 3 14B
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	−15%
Qwen3-235B-A22B Instruct (2507) Alibaba Cloud	$0.1717	$0.09	$0.58	262K		−14%
Llama 3.3 70B Meta	$0.175	$0.13	$0.40	128K	Dec 2023	−13%
Qwen3.5-27B Alibaba Cloud	$0.19	$0.09	$0.69	262K		−5%
Hy3 Tencent	$0.1967	$0.13	$0.53	262K		−2%
Ministral 3 14B This model Mistral	$0.20	$0.20	$0.20	256K
Qwen3.8-Flash Alibaba Cloud	$0.2033	$0.15	$0.47	1M		+2%
Qwen3-VL-8B Alibaba Cloud	$0.2083	$0.15	$0.50	262K		+4%
Qwen-MT-Turbo Alibaba Cloud	$0.215	$0.16	$0.49	16K		+8%
Command R 08-2024 Cohere	$0.225	$0.15	$0.60	128K	Jun 2024	+13%
GPT-4o Mini OpenAI	$0.225	$0.15	$0.60	128K	Oct 2023	+13%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Thunder Compute

RTX A6000 from $0.35, A100 from $1.09, per GPU per hour

Billed per minute, no commitment, no minimums

One click into VS Code or Cursor, no SSH setup

See live pricing

Capabilities

What Ministral 3 14B accepts and can do, as published by Mistral.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
File upload Process uploaded documents, spreadsheets, and other files.

Common questions

What is Ministral 3 14B good for?

Local and edge deployment with vision. Apache 2.0 weights at the heavy end of the Ministral 3 family, still on a single consumer GPU.

When is Ministral 3 14B not a good fit?

Audio or video input, and tasks that need a bigger model, where Mistral Small 4 and Mistral Large 3 sit above it. No maximum output length is published.

What is the cheapest way to run Ministral 3 14B?

Hosted, unless you push serious volume. Mistral charges $0.20 in / $0.20 out per 1M tokens. The cheapest rental that fits is 1x RTX 4060 Ti at $86 a month, which costs the same as about 432M tokens a month on that API.

Can I self-host Ministral 3 14B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 12 GB of GPU memory, which starts at roughly $86 a month on the cheapest rental that fits.