Skip to content
Seedance 2.0 Face is here — generate video from real-person reference photos.Try it now →
Back to Models
meta-llamameta-llama·Apr 5, 2025

Meta: Llama 4 Maverick

meta-llama/llama-4-maverick
context
1.0M
Max Output
16.4K
Input / 1M
$0.15
Output / 1M
$0.60

About

Llama 4 Maverick is a multimodal model from Meta built on a mixture-of-experts (MoE) architecture with 128 routed experts and a shared expert, activating 17 billion parameters per forward pass out of 400B total. It accepts text and image input and produces text and code output across 12 supported languages, using early fusion for native multimodality and a 1 million token context window. Trained on roughly 22 trillion tokens with a knowledge cutoff in August 2024, it is instruction-tuned for assistant-style interaction, image reasoning, and tool use. On the LMArena chat leaderboard it reached an ELO score of 1417, and it performs comparably to DeepSeek V3 on reasoning and coding with fewer active parameters. Released April 5, 2025 under the Llama 4 Community License.

Capabilities

Context Length
1.0M
Max Output
16.4K
Reasoning
No
In
text, image
Out
text

Benchmarks

View leaderboard
14.3#98 of 133
Intelligence Index
15.6#100 of 118
Coding Index
19.3#56 of 63
Math Index

Reasoning & Knowledge

MMLU-Pro80.9%
GPQA Diamond67.1%
HLE4.8%

Coding & Agentic

LiveCodeBench39.7%
SciCode33.1%
Terminal-Bench Hard6.8%

Math

AIME 202519.3%

Source: Artificial Analysis

Pricing

Full pricing
TypePrice / 1M tokens
Input$0.15
Output$0.60

API

API reference

OpenAI-compatible · Model ID meta-llama/llama-4-maverick

curl https://api.elliotgate.com/v1/chat/completions \
  -H "Authorization: Bearer sk-omg-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-maverick",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OFTEN COMPARED

Llama 4 Maverick comparisons

Decide which model wins on the dimensions that matter for your workload — context, benchmarks, pricing, or serving latency.