RentGPU RentGPU
Find a GPU →
by Mistral AI

Mistral: Ministral 8B.

text closed 128K ctx
Cheapest input
$0.11/M
on OpenRouter
Cheapest output
$0.11/M
on OpenRouter
Hosted equiv.
~$0.04/hr
@ 100 tok/s on OpenRouter

Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length...

Hosted API only

No self-host path — closed weights.

Mistral: Ministral 8B's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.11 $0.11 Launch ↗
FAQ

Frequently asked.

How do I run Mistral: Ministral 8B?
Mistral: Ministral 8B is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Mistral: Ministral 8B?
Mistral: Ministral 8B is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Mistral: Ministral 8B?
API pricing starts at $0.11/M input tokens and $0.11/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Mistral: Ministral 8B open-source or proprietary?
Mistral: Ministral 8B is a proprietary model from Mistral AI. Access is API-only — there are no public weights to download.