Available models.
Prices are in USD per 1M tokens, checked on 5 Nov 2026. Prices are set by the provider and change. Official pricing
| Model | What it does | Parameters | Price per 1M tokens (input / output) |
|---|---|---|---|
| Llama 4 Maverick | A multimodal text-and-image model, the most capable of the available Llama 4 models. | 400B parameters, 17B active (MoE) | Free licenceYour cost is the hardware. We check the licence terms. |
| Llama 4 Scout | A multimodal model with an extremely long context, up to 10M tokens. | 109B parameters, 17B active (MoE) | Free licenceYour cost is the hardware. |
| Llama 3.3 70B | A text model with large-model quality on a single powerful server. | 70B parameters, 128K context | Free licenceYour cost is the hardware. |
| Llama 3.1 405B | The largest dense Llama model, for the most demanding tasks on your own hardware. | 405B parameters, 128K context | Free licenceNeeds server-class GPUs. |
| Llama 3.1 8B | A small, fast model that runs even on a desktop machine. | 8B parameters, 128K context | Free licenceYour cost is the hardware. |
What it is good for.
A good fit for company assistants, search across internal documents and automation where data must not leave. It comes in several sizes, from small to very powerful, so we match it to your hardware. It can be fine-tuned on your own material.
What to use it with.
Meta has no tool of its own. We recommend OpenCode with the model running on your side.
OpenCodeAn open agent that connects to a model running on your side as well as to cloud providers.We also connect it to
OpenCode
Hermes
OpenClawBERCIK CodeWhere it runs.
In the cloud
AvailableYou can also use Llama as a service from cloud providers if you do not want to manage your own hardware.
On your side
AvailableThe model weights are open. We run them on hardware in your company, your data never leaves your network and you do not pay per request. We check the licence before deployment.
Want to work with Llama?
Tell us what you need. We will recommend a version and hardware, or another model if it fits better.
Let's discuss what comes next for your business.
Write a few lines about what you do. We reply the same day and book twenty minutes on the phone.
Tap a photo to see the contact.
Filip Berčík
Websites, SEO, AEO, AI infrastructure project manager, 3D modeling, software development
774 915 200 aetheron@aetheron.czPrague