Model specification · Meta

Llama 4 Scout

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...

SpecificationsReported values
Context window
1.3M
Maximum output
16K
Architecture
text+image->text
Tokenizer
Llama4
Knowledge cutoff
2024-08-31
Moderated
No
Input modalities
text image
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.100 / M
Output$0.300 / M
Benchmark indexesReported indexes
Intelligence
10
Coding
8.2
Agentic
1.1
Design Arena Elo
829
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00130
Long analysis100K / 4K × 150%$0.011
Workday20K / 2K × 1,00030%$2.60
More from MetaAll Meta models
ModelContextInput / MOutput / MIntel.
Llama 4 Maverick1.0M$0.200$0.80014.3
Llama 3.3 70B Instruct131K$0.130$0.4009.4
Llama 3.1 8B Instruct131K$0.050$0.0807.6