Model catalogLlama
Llama 4 Scout
Meta's Llama 4 as a capable general assistant. Served with vLLM behind your own private, OpenAI-compatible /v1 endpoint — billed by the second, terminate anytime.
109B MoE · 17B act · FP8 · 256K context · 2× 80 GB · per-second billing
01Specifications
The specs the launcher enforces.
Architecture, served precision, max context, and the minimum GPU shape — the numbers that decide how Llama 4 Scout runs and what it costs.
| Spec | Value |
|---|---|
| Architecture | 109B MoE · 17B act |
| Served precision | FP8 |
| Max context | 256K |
| Minimum GPU shape | 2× 80 GB |
Runs on 2× 80 GB · billed per second — final cost depends on the GPU shape.
Full pricing →02How it runs
A private endpoint, not a shared API.
Launching Llama 4 Scout runs the model on your own instance and gives you a private, OpenAI-compatible /v1 endpoint and API key. Point any OpenAI-compatible SDK at your base URL, change the model name, and existing code works. The endpoint is yours alone — terminate the instance and it goes away with it.
Billing is by the second on the 2× 80 GB shape the launcher enforces, from boot to terminate. No commitment and no tier gates.
Gated model
Llama 4 Scout is a gated repository on Hugging Face. Accept the model's license on Hugging Face, and the launch flow injects your own token so the instance can pull the weights.
03Get started
Launch Llama 4 Scout now.
One private OpenAI-compatible endpoint, one key, billed by the second. The console opens with Llama 4 Scout preselected.