Meta
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
At a glance
- Input / 1M
- $0.19
- Output / 1M
- $0.65
- Context
- 1.05M
- Max output
- 16K
- Intelligence
- 10
- Released
- Apr 2025
Pricing
Llama 4 Maverick API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.19 |
|---|---|
| Output tokensPer 1M tokens | $0.65 |
| Cached input (read)Per 1M tokens | $0.05 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.70
per 1,000 requests
Coding task
30K in, 4K out
$8.24
per 1,000 requests
Long document summary
150K in, 2K out
$29.43
per 1,000 requests
Benchmarks
Llama 4 Maverick benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
10
Coding index
16.3
Agentic index
0.6
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 1.05M tokens
- Max output
- 16K tokens
- Input types
- Image, Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- April 5, 2025
- Knowledge cutoff
- August 31, 2024
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Llama 4 Maverick vs other models
See how Llama 4 Maverick stacks up head to head on price, benchmarks, and features.
Llama 4 Maverick vs Gemini 2.5 Flash Lite
Meta vs Google
See comparison
Llama 4 Maverick vs GPT-4o-mini
Meta vs OpenAI
See comparison
Llama 4 Maverick vs Qwen3 235B A22B Instruct 2507
Meta vs Qwen
See comparisonLlama 4 Maverick vs Llama 3.3 70B Instruct
Meta vs Meta
See comparisonLlama 4 Maverick vs Qwen3 Coder Next
Meta vs Qwen
See comparisonLlama 4 Maverick vs Qwen3 Next 80B A3B Instruct
Meta vs Qwen
See comparisonAlternatives
Llama 4 Maverick alternatives
Similar models worth considering, and where each one has the edge.
Qwen
Qwen3 235B A22B Instruct 2507
Mistral
Mistral Small 4
Z.ai
GLM 4.5 Air
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Llama 4 Maverick cost?
Llama 4 Maverick costs $0.19 per 1M input tokens and $0.65 per 1M output tokens through the API. A typical chat message costs about $0.70 per 1,000 messages.
What is the context window of Llama 4 Maverick?
Llama 4 Maverick accepts up to 1.05M tokens of input and can write up to 16K tokens in a single response.
What is the best alternative to Llama 4 Maverick?
Qwen3 235B A22B Instruct 2507 from Qwen is a strong alternative. It offers: 1.2x cheaper output, higher intelligence score, newer release.
Can I use Llama 4 Maverick alongside other models?
Yes. Shortcut Chat sends one prompt to Llama 4 Maverick and any other models you pick at the same time, so you can compare answers side by side.
Try Llama 4 Maverick next to every other model.
Use Llama 4 Maverick alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.