Speed
Output tokens / second
Llama 4 Maverick overview
Llama 4 Maverick by Meta
Llama 4 Maverick is a high-performance AI model from Meta, utilizing a mixture-of-experts architecture to excel in reasoning and coding tasks.
Llama 4 Maverick specs
- Developer
- Meta
- Input
- Text, Image
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Overview
Llama 4 Maverick employs a mixture-of-experts architecture, featuring 128 experts with a total of approximately 400 billion parameters, utilizing 17 billion active parameters per token. This design enables it to outperform models like GPT-4o and Gemini 2.0 in coding and reasoning benchmarks.
Key Features
- Mixture-of-Experts Architecture: Utilizes 128 experts for enhanced performance.
- Multimodal support for text and images across 12 languages.
- Cost-effective deployment options with FP8 quantization for efficiency.
Intended Use
- Complex Problem Solving: Handles advanced reasoning tasks effectively.
- Code Generation and Analysis: Excels in creating and understanding complex code structures.
- Multimodal Applications: Designed for multilingual assistants, creative writing, visual storytelling, and coding applications.
Architecture
The model employs Meta’s mixture-of-experts (MoE) framework with active parameter counts of 400 billion. Maverick utilizes a large pool of 128 experts for task-specific activation.
Training Data
Trained on curated datasets including multilingual corpora, image datasets, and synthetic reasoning examples.
API Documentation:
Detailed API Documentation is available here.
Use cases
- Enterprise-scale multimodal AI applications
- Large document processing and legal/financial analysis
- AI-powered virtual assistants with visual context understanding
- Coding assistance and large-scale codebase comprehension
- Personalized user interaction based on extensive data
Capabilities
- Function calling
- Streaming
- Structured outputs
Llama 4 Maverick benchmarks by 
Artificial Analysis
See how Llama 4 Maverick compares in generation speed and latency. Data retrieved Nov 3, 2026.
Benchmark results
Compare 6 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
Terminal-Bench 4.0
Agentic tasks completed in a command-line environment.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
Llama 4 Maverick API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.351 | 1M tokens |
| Output | $1.1 | 1M tokens |
Llama 4 Maverick is unlisted on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Llama 4 Maverick vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Llama 4 Maverick | $0.351 | $1.1 |
| Muse Glimmer 30B | $0.3703 | $1.59 |
| Muse Spark Open | $1.32 | $4.5 |
| Muse Spark 1.3 | $1.32 | $4.5 |
| Muse Wonder | $4.23 | $21.16 |
Models similar to Llama 4 Maverick
Related articles
Llama 4 Maverick FAQ
Does Llama 4 Maverick support streaming?
Yes, Llama 4 Maverick can stream responses as they are generated.
Does Llama 4 Maverick support tool calling and structured outputs?
Yes, Llama 4 Maverick supports both function calling and structured outputs.
Who created Llama 4 Maverick?
Llama 4 Maverick was built by Meta.
What API endpoint is used to access Llama 4 Maverick?
Llama 4 Maverick is accessed through the v1/chat/completions endpoint.