Model specification · Meta

Llama 4 Maverick

meta-llama/llama-4-maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

SpecificationsReported values
Context window
1.0M
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$0.200 / M
Output$0.800 / M
Benchmark indexesReported indexes
Intelligence
14.3
Coding
16.3
Agentic
1.3
Design Arena Elo
916
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00280
Long analysis100K / 4K × 150%$0.023
Workday20K / 2K × 1,00030%$5.60
More from MetaAll Meta models
ModelContextInput / MOutput / MIntel.
Llama 4 Scout1.3M$0.100$0.30010
Llama 3.3 70B Instruct131K$0.130$0.4009.4
Llama 3.1 8B Instruct131K$0.050$0.0807.6