Mistral AI logo

Rent Mistral 7B in a private loop

Fast foundational model
By Mistral AImistral:7b7B parameters32K tokens of contextApache 2.0

An Apache 2.0 classic: undemanding, very fast and fully free for commercial use. It trails newer 7B models on quality but is predictable and needs almost no resources — handy as a cheap filter in front of a bigger model.

GPU configurations for Mistral 7B

1x V100

Best value
~28 tok/sup to 2 streams
$0.22per hour

1x RTX4090

~82 tok/sup to 4 streams
$0.64per hour

1x RTX5090

~108 tok/sup to 6 streams
$0.65per hour

1x A100

~72 tok/sup to 8 streams
$1.47per hour

1x H100

~118 tok/sup to 16 streams
$3.33per hour
Pick a GPU
VRAM
RAM
Storage
vCPU
CPU

Billing follows server uptime by the hour.

Mistral 7B benchmarks

as published by the model vendor
Mistral 7B scores in public benchmarks
MMLU62.5
GSM8K52.2
HumanEval39.4

Other models in the private loop

FAQ

Frequently asked about renting Mistral 7B

Which GPU does Mistral 7B need?

The entry configuration is 1x V100, which delivers around 28 tokens per second. For more parallel requests and headroom on speed, go with 1x H100.

How much does Mistral 7B cost?

An hour of Mistral 7B runs from $0.22 to $3.33 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.

How do I call Mistral 7B from my code?

Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass mistral:7b as the model name. Code written against the OpenAI API needs no changes.

Does the data stay private?

Yes. Mistral 7B runs on a dedicated GPU server inside a private loop: requests and responses never reach the model vendor and are not used for training.

What context window and license does Mistral 7B have?

Mistral 7B holds 32K tokens of context per request and ships under the Apache 2.0 license, so you can use it commercially on your own hosting terms.