Llama 4 Maverick
MetaLlamaOpen WeightLlama 4 Community License Agreement
Description
Llama 4 Maverick is a natively multimodal model capable of processing both text and images. It features a 17 billion active parameter mixture-of-experts (MoE) architecture with 128 experts, supporting a wide range of multimodal tasks such as conversational interaction, image analysis, and code generation. The model includes a 1 million token context window.
Release Date
2025-04-05
Parameters
400.0B
Context Length
524K
Modalities
image, text
Capability Radar
80
general
40
coding
80
reasoning
60
scienceest.
68
agents
90
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 105 | 41.0 | LS |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
85.5%SR
Language
MMLU-Pro
80.5%SR
TydiQA
31.7%SR
Math
MGSM
92.3%SR
MathVista
73.7%SR
MATH
61.2%SR
Multimodal
MMMU
73.4%SR
Reasoning
ChartQAMasry et al. (2022)
90.0%SR
MBPP
0.78 / 100SR
GPQANYU + Cohere + Anthropic (2023)
69.8%SR
LiveCodeBench
43.4%SR
Vision
DocVQADocVQA (2020)
94.4%SR
MMMU-Pro
59.6%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Image To Text90
Language80
Legal80
Math80
Multimodal80
Finance80
General80
Healthcare80
Vision80
Physics70
Reasoning70
Biology70
Chemistry70
Code40
Pricing
Input Price$0.25 / 1M tokens
Output Price$0.97 / 1M tokens
Blended Price (3:1)$0.35 / 1M tokens
Cache Read Price$0.17 / 1M tokens
Speed
Tokens/sec85.8
Time to First Token0.98s
Time to Answer0.98s
Provider Price Ranking
Provider Price Ranking
8 providers
Cheapest: HeliconeMost Expensive: Neon
ProviderInputOutput
1HeliconeCheapest
$0.15
$0.6
2DeepInfra
$0.2
$0.8
3MetaPRIMARY
$0.25
$0.97
4DigitalOcean
$0.25
$0.87
5NanoGPT
$0.35
$1
6OpenRouter
$0.35
$1
7Kilo Gateway
$0.35
$1
8Neon
$0.5
$1.5
Compare pricing across different API providers for this model.