RentGPU RentGPU
Trouver un GPU →
by Meta AI

Meta Llama 3.1 405B Instruct.

text open weights datacenter 405B params 4K ctx
Cheapest input
$3.5/M
on Together AI
Cheapest output
$3.5/M
on Together AI
Smallest GPU
1× AMD MI325
Smallest GPU to run it See all quantisations →

1× AMD MI325.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Together AI hosted inference $3.5 $3.5 Launch ↗
FAQ

Frequently asked.

How do I run Meta Llama 3.1 405B Instruct?
Meta Llama 3.1 405B Instruct is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Meta Llama 3.1 405B Instruct?
Meta Llama 3.1 405B Instruct is available via Together AI. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Meta Llama 3.1 405B Instruct?
API pricing starts at $3.5/M input tokens and $3.5/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Meta Llama 3.1 405B Instruct open-source or proprietary?
Meta Llama 3.1 405B Instruct is open-weight under the license. You can download and self-host it.