Llama 4 Maverick
Llama 4 Maverick is a large language model made by Meta, added to the catalog on 5 Apr 2025. It has a context window of 524,288 tokens and costs $0.35 per 1M input tokens and $1.00 per 1M output tokens. It accepts text and images and produces text. Typical uses: enhance multilingual content creation, improve vision-language task performance and develop interactive multimodal applications.
Price checked ยท source: OpenRouter
What Llama 4 Maverick is
Meta's Llama 4 Maverick, released on April 5, 2025, is a powerful multimodal language model designed to handle both text and image inputs. Built with a mixture-of-experts architecture, it features 128 experts and 17 billion active parameters per forward pass, with a total of 400 billion parameters. Maverick supports multilingual text and code output in 12 languages. With a 1 million token context window, it excels in vision-language tasks, offering instruction-tuned, assistant-like behavior. Whether for research or commercial use, Maverick is optimized for advanced multimodal interaction.
Key features
- 17 billion active parameters per forward pass
- Multimodal: text and image input
- Supports 12 languages for output
- 1 million token context window
- Instruction-tuned for assistant-like tasks
Typical uses
- Enhance multilingual content creation
- Improve vision-language task performance
- Develop interactive multimodal applications
- Facilitate advanced research projects
Llama 4 Maverick pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.35 |
| Output, per 1M tokens | $1.00 |
| Cached input read, per 1M tokens | $0.17 |
No price change since it was added on 5 Apr 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0096 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.013 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.054 |
Llama 4 Maverick specifications
| Model id | meta-llama/llama-4-maverick |
|---|---|
| Version | llama-4-maverick-17b-128e-instruct |
| Context window | 524,288 tokensAbout 393,216 English words |
| Max output | 32,768 tokens |
| Knowledge cutoff | 2024-08-31 |
| Added to catalog | 5 Apr 2025 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
The integration of AI is poised to revolutionize the way we work, play, and create. By automating mundane and repetitive tasks, AI can free up human time and energy for more creative and high-value pursuits. In the workplace, AI can augment human capabilities, enabling professionals to focus on strategic and innovative tasks. In leisure, AI-powered tools can help people discover new hobbies and interests, or enhance their existing ones. For instance, AI-assisted music composition can enable individuals to create complex musical pieces without extensive musical training. Moreover, AI can facilitate creativity by generating new ideas, exploring novel patterns, and collaborating with humans in the artistic process. As a result, people may have more time to pursue their passions, and creativity may flourish as humans are able to focus on high-level thinking and imagination. This could lead to a more fulfilling and enjoyable life.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.
Compare Llama 4 Maverick
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.