/ Models

Language models

Meta: 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...

Maker
Meta-llama
Context window
1.3M
Max output
16K
Input / 1M
$0.1
Output / 1M
$0.3
1M in + 1M out
$0.4

Everything else

Max output16K
Input / 1M$0.1
Output / 1M$0.3
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.4
Takestext, image
Returnstext
Toolsyes
Reasoningno
Open weightsyes
Released2025-04-05
Knowledge cutoff2024-08-31
Retires
Catalog idmeta-llama/llama-4-scout

Benchmarks

sourceepoch
eci130.54
confidenceLikely
accessibilityOpen weights (restricted use)

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models