Llama 4 Scout
Pilot $4,900 fixed
- Sizes
- 109B MoE
- Active params
- 17B
- Context
- 10M (claimed)
- Licence
- Llama 4 Community License · conditions
- Fits on
- 1× H100 80GB at 4-bit, 1× H200 141GB at FP8
- Endpoint
- llm.yourcompany.internal/v1
- Egress
- 0
- Owner
- YOU
Llama 4on your own GPUs.
Llama 4 Scout and Maverick served from GPUs you control, behind an OpenAI-compatible endpoint. Prompts and documents stay inside your network.
This card is the installation. Pick a size on its edge and it is re-issued.
The 72-hour pilot with Llama 4.
$4,900 fixed. Scout is the single-GPU option at 4-bit. Maverick is the larger model and needs a multi-GPU node.
Live on your data
72 h$4,900 fixed
Llama 4 live on your data in 72 hours. The clock starts after access and prerequisites.
Your endpoint
/v1OpenAI-compatible
OpenAI-compatible endpoint. Your applications switch by changing the base URL.
Your hardware
- Llama 4 Scout1× H100 80GB at 4-bit, 1× H200 141GB at FP8
- Llama 4 Maverick4× H100 (320GB) at 4-bit, 8× H100 (640GB) at FP8
The readout
Evalon your data
Reference evaluation on your data. Readout and production scoping.
We size the hardware and source it at cost, with no markup. Ballpark: one H100 80GB ≈ $25–30k; a 4×H100 node ≈ $180–240k; smaller models run on far less.
Same SDK. Change the base URL.
The model is one parameter. Everything else in your application stays as it is.
client = OpenAI(
base_url="https://llm.yourcompany.internal/v1", # inside your network
api_key="your-key",
)
reply = client.chat.completions.create(
model="llama-4-scout",
messages=[{"role": "user", "content": "Summarise this contract."}],
)Licence, plainly.
- Llama 4 ScoutLlama 4 Community License · conditionsCommercial use: with conditions
- Llama 4 MaverickLlama 4 Community License · conditionsCommercial use: with conditions
Llama 4 is released by Meta under the Llama 4 Community License, not an open-source licence. It allows commercial use, with conditions.
Products and services built on it must show "Built with Llama". Meta's acceptable use policy applies to your users. Services above 700 million monthly users need a separate licence from Meta, and the licence has a regional clause on multimodal use.
We read the current licence text against your use when we scope the pilot.
Built with Llama This page is the notice Meta's licence asks for. It appears wherever a product built on Llama is presented.
Published by Meta. We are not affiliated with the vendor. This is a summary, not legal advice.
Related models.
- Gemma 4Google2 models, from 1× T4 16GB at 4-bitApache 2.0
- Qwen3AlibabaCPU only at 4-bitApache 2.0
- DeepSeek V3 / R1DeepSeek8× H100 (640GB) at 4-bitMIT (R1); DeepSeek Model Agreement (V3) (use policy (V3))
Talk to an engineer.
Tell us the model, the data and the GPUs you have. An engineer from Limassol or Auckland scopes the 72-hour pilot with you.