Home
LLMs
Ministral 3 8B

Ministral 3 8B

The mid-size Ministral 3 model between the 3B and 14B variants, an 8B dense model with a vision encoder under Apache 2.0, built for edge deployment in base, instruct and reasoning variants.

Params: 8.8B
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: $0.15 /1M
Output: $0.15 /1M
Hosted by: 1 provider

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 8B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Ministral 3 8B, 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	$0.15	$0.15	$1.80	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 8B needs about 9 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 576M 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 8B 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	9 GB25 GB	1× RTX 4060 Ti	$86$173	576M tokens /mo1B tokens /mo
8-bit FP8 / INT8	13 GB29 GB	1× RTX 4060 Ti	$86$173	576M tokens /mo1B tokens /mo
16-bit FP16 / BF16	24 GB55 GB	2× RTX 4060 Ti	$173$346	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 8B by blended rate, each at its own cheapest provider.

Models priced nearest Ministral 3 8B per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Ministral 3 8B
Gemma 3 27B Instruct Google Cloud	$0.1333	$0.10	$0.30	128K	Aug 2024	−11%
Gemma 4 26B A4B Google Cloud	$0.1333	$0.10	$0.30	256K	Jan 2025	−11%
Qwen3-32B FP8 Alibaba Cloud	$0.1333	$0.10	$0.30	33K		−11%
Gemini 2.5 Flash-Lite Google Cloud	$0.15	$0.10	$0.40	1M	Jan 2025	0%
GPT-4.1 Nano OpenAI	$0.15	$0.10	$0.40	1M	Jun 2024	0%
Ministral 3 8B This model Mistral	$0.15	$0.15	$0.15	256K
Qwen3.5-Flash Alibaba Cloud	$0.15	$0.10	$0.40	1M		0%
Llama 3.2 11B Vision Meta	$0.155	$0.05	$0.68	128K	Dec 2023	+3%
Nemotron 3 Super 120B A12B Nvidia	$0.1583	$0.09	$0.50	1M	Jun 2025	+6%
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	+13%
Qwen3-235B-A22B Instruct (2507) Alibaba Cloud	$0.1717	$0.09	$0.58	262K		+14%

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.

Salad

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Capabilities

What Ministral 3 8B 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 8B good for?

Edge deployment with text and image input. Apache 2.0 weights in the middle of the Ministral 3 family, small enough for a single consumer GPU.

When is Ministral 3 8B not a good fit?

Audio or video input, and tasks that need a bigger model than 8B. No maximum output length is published.

What is the cheapest way to run Ministral 3 8B?

Hosted, unless you push serious volume. Mistral charges $0.15 in / $0.15 out per 1M tokens. The cheapest rental that fits is 1x RTX 4060 Ti at $86 a month, which costs the same as about 576M tokens a month on that API.

Can I self-host Ministral 3 8B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 9 GB of GPU memory, which starts at roughly $86 a month on the cheapest rental that fits.