Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Meta
meta-llama/llama-4-scoutCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
Meta meta-llama/llama-4-scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Llama 4 Scout earns a request when it needs tool calls, very long inputs, image input; a short, general request would go to Nemotron 3.5 Super VL (free) instead - free per million input tokens against $0.10 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs Llama 4 Scout
targets:
- id: llama-4-scout
kind: llm
name: Llama 4 Scout
metadata:
model: meta-llama/llama-4-scout # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 1310720
cost:
usd_per_1k_tokens: 0.000200Input list price per million tokens; Llama 4 Scout is the 4th cheapest of 8 listed.
Photo: RDNE Stock project
A higher intelligence index, best first, with the price it comes at.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
