Mistral logo Retired Jul 2026 Open weights · Apache 2.0

Mistral NeMo

A 12B model built by Mistral AI with NVIDIA under Apache 2.0, released July 2024, that runs on a single GPU with multilingual support.

Jump to: Specs Pricing Self-hosting Similar models FAQ More from Mistral
Visit website Compare vs other LLMs →
Cheapest via Novita
Input
$0.04 /1M tokens
Output
$0.17 /1M tokens
Novita Mistral 2 providers

Key Specifications

Context window
128K tokens
Max output
33K tokens
Released
Parameters
12B
Inputs
Text

Hosted API pricing

Provider Input /1M tokens Output /1M tokens Cost at 10M in + 2M out
Novita logo Novita $0.04 $0.17 $0.74 View
Mistral logo Mistral Creator Open weights, no hosted price View

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 NeMo needs about 11 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 1× RTX 4060 Ti at about $79 a month.

That costs the same as roughly 1B tokens a month on Novita's API. Self-hosting is more expensive below that volume.

Fits on 1 Single node ≤ 8
Precision Memory Cheapest fit (32K context) Cost /mo Break-even vs API
4-bitINT4 / FP4
11 GB
Nvidia logo 1× RTX 4060 Ti
$79
1B tokens /mo
8-bitFP8 / INT8
19 GB
Nvidia logo 2× RTX 3060
$86
1B tokens /mo
16-bitFP16 / BF16
31 GB
Nvidia logo 4× RTX 3060
$173
3B 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 Mistral NeMo by blended rate, each at its own cheapest provider.

Model Blended /1M vs Mistral NeMo
Alibaba Cloud Qwen3.7-Flash Alibaba Cloud $0.0467 −24%
OpenAI GPT-OSS-20B OpenAI $0.0483 −22%
Cohere Command R7B Cohere $0.0583 −5%
Google Cloud Gemma 3 12B Instruct Google Cloud $0.0583 −5%
Meta Llama 3.2 1B Meta $0.0583 −5%
Mistral Mistral NeMo This model Mistral $0.0617
OpenAI GPT-OSS-120B OpenAI $0.0633 +3%
Nvidia Nemotron 3 Nano 30B A3B Nvidia $0.075 +22%
Meta Llama 3 8B Meta $0.0833 +35%
Alibaba Cloud Qwen3-Coder-30B-A3B Alibaba Cloud $0.0917 +49%
Meta Llama 3.2 3B Meta $0.0983 +59%

Prices are 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.

Frequently Asked Questions

What is Mistral NeMo good for?

Multilingual text generation on your own hardware. Apache 2.0 weights, small enough for a single consumer GPU.

When is Mistral NeMo not a good fit?

Hosted use: Mistral retired it from its own API in July 2026. Text only, with no function calling or structured output.

What is the cheapest way to run Mistral NeMo?

Hosted, unless you push serious volume. Novita charges $0.04 in / $0.17 out per 1M tokens. The cheapest rental that fits is 1x RTX 4060 Ti at $79 a month, which costs the same as about 1B tokens a month on that API.

Can I self-host Mistral NeMo?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 11 GB of GPU memory, which starts at roughly $79 a month on the cheapest rental that fits.

More from Mistral

Model Context Input /1M Output /1M
Mistral Ministral 3 3B Open weights 256K $0.10 $0.10
Mistral Ministral 3 8B Open weights 256K $0.15 $0.15
Mistral Ministral 3 14B Open weights 256K $0.20 $0.20
Mistral Mistral Small 4 Open weights 256K $0.15 $0.60
Mistral Codestral 128K $0.30 $0.90
Mistral Mistral Large 3 Open weights 256K $0.50 $1.50
Mistral Mistral Medium 3.5 Open weights 256K $1.50 $7.50
Mistral Devstral Medium 128K