Mistral Large 4

Mistral's new flagship, a granular mixture-of-experts with about 1T total and 52B active parameters plus a vision encoder, combining instruction following, reasoning and agent work in one model.

Params: 1.1T, 52B active
Context: 1M tokens
Released: Oct 2026
License: Mistral Ecosystem Open-Weight License

Visit Mistral Compare vs other LLMs →

Hosted API price

List price via Mistral · per 1M tokens

USD

Input: $0.70 /1M
Output: $2.10 /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 Mistral Large 4, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Mistral Large 4, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
Mistral Creator	$0.70	$2.10	$0.07	$11.20	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

Mistral Large 4 needs about 581 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX PRO 6000 at about $13,478 a month.

That costs the same as roughly 14B tokens a month on Mistral's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Mistral Large 4 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 1M context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	581 GB621 GB	8× RTX PRO 6000	$13,478$13,478	14B tokens /mo14B tokens /mo
8-bit FP8 / INT8	1,053 GB1,094 GB	8× B200	$46,022$46,022	49B tokens /mo49B tokens /mo
16-bit FP16 / BF16	2,105 GB2,185 GB	– –	––	––

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. Pricing methodology.

Similarly priced models

The models nearest Mistral Large 4 by blended rate, each at its own cheapest provider.

Models priced nearest Mistral Large 4 per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Mistral Large 4
DeepSeek V3 DeepSeek		$0.85		128K
GLM-4.7 Z.AI	$0.8667	$0.60	$2.20	205K		−7%
DeepSeek V3.1 DeepSeek	$0.896	$0.672	$2.016	131K		−4%
Gemini 3 Flash Preview Google Cloud	$0.9167	$0.50	$3.00	1M	Jan 2025	−2%
Qwen3.6-Plus Alibaba Cloud	$0.9167	$0.50	$3.00	1M		−2%
Mistral Large 4 This model Mistral	$0.9333	$0.70	$2.10	1M
Nemotron 3 Ultra 550B A55B Nvidia	$0.99	$0.66	$2.64	1M	Sep 2025	+6%
DeepSeek R1 DeepSeek	$1.00	$0.70	$2.50	128K		+7%
DeepSeek R1 Turbo DeepSeek	$1.00	$0.70	$2.50	64K		+7%
Llama 3 70B Meta	$1.00	$0.65	$2.75	8K	Dec 2023	+7%
Kimi K2.6 Moonshot AI	$1.0333	$0.60	$3.20	262K		+11%

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.

GPUhub

Fully Dedicated GPU Servers

No Virtualization. No Shared GPUs

Stable Performance for AI Training & Inference

Full Control for Production Workloads

Learn more

Capabilities

What Mistral Large 4 accepts and can do, as published by Mistral.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
Web search Search the web for up-to-date information.
Code execution Write and execute code in a sandboxed environment.
File upload Process uploaded documents, spreadsheets, and other files.
Image generation Generate and edit images from text prompts.

Common questions

What is Mistral Large 4 good for?

General multimodal and agent work at the top of Mistral's lineup, with reasoning and instruction following in one model. Weights under the Mistral Ecosystem Open-Weight License allow commercial self-hosting, on more than one node.

When is Mistral Large 4 not a good fit?

Model-as-a-service businesses, which need a separate commercial license from Mistral, and modest hardware: memory follows the full 1T parameters, not the 52B active. It is a public preview, and no maximum output length or knowledge cutoff is published.

What is the cheapest way to run Mistral Large 4?

Hosted, unless you push serious volume. Mistral charges $0.70 in / $2.10 out per 1M tokens. The cheapest rental that fits is 8x RTX PRO 6000 at $13,478 a month, which costs the same as about 14B tokens a month on that API.

How does Mistral Large 4 compare with Mistral Large 3?

Same text and image input. Mistral Large 4 lists at 40% more per 1M input tokens and 40% more per 1M output tokens than Mistral Large 3. It came out 10 months later, has a larger context (1M against 256K tokens) and more parameters (1.1T with 52B active against 675B with 41B active) and is licensed under Mistral Ecosystem Open-Weight License against Apache 2.0.

Can I self-host Mistral Large 4?

Yes. The weights are released under the Mistral Ecosystem Open-Weight License. At 4-bit it needs about 581 GB of GPU memory, which starts at roughly $13,478 a month on the cheapest rental that fits.