Llama 4 Scout
Llama 4 Scout is a large language model made by Meta, added to the catalog on 5 Apr 2025. It has a context window of 1,310,720 tokens and costs $0.10 per 1M input tokens and $0.30 per 1M output tokens. It accepts text and images and produces text. Typical uses: engage in multilingual chat interactions, generate accurate image captions and perform complex visual reasoning.
Price checked ยท source: OpenRouter
What Llama 4 Scout is
Meta's Llama 4 Scout, released on April 5, 2025, is a versatile AI model designed for a range of applications, from multilingual chat to visual reasoning. With a context window of 10 million tokens, it efficiently processes both text and image inputs to generate text outputs. The model utilizes 17 billion active parameters out of a total of 109 billion, enabling it to handle complex tasks seamlessly. Llama 4 Scout is particularly well-suited for assistant-style interactions and is instruction-tuned for tasks like captioning and image understanding. Its multilingual capabilities extend across 12 languages, making it a robust choice for global applications.
Key features
- 17 billion active parameters in MoE architecture
- Processes text and image inputs
- Generates text outputs in 12 languages
- 10 million token context length
- Instruction-tuned for diverse tasks
Typical uses
- Engage in multilingual chat interactions
- Generate accurate image captions
- Perform complex visual reasoning
- Deploy in local or commercial settings
Llama 4 Scout pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.10 |
| Output, per 1M tokens | $0.30 |
No price change since it was added on 5 Apr 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0027 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0036 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.015 |
Llama 4 Scout specifications
| Model id | meta-llama/llama-4-scout |
|---|---|
| Version | llama-4-scout-17b-16e-instruct |
| Context window | 1,310,720 tokensAbout 983,040 English words |
| Max output | 16,384 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 advent of Artificial Intelligence (AI) is poised to revolutionize work, leisure, and creativity. AI can automate mundane and repetitive tasks, freeing humans to focus on high-value tasks that require creativity, empathy, and problem-solving. This shift can lead to a more fulfilling work experience, increased productivity, and a better work-life balance. In leisure, AI-powered virtual reality and augmented reality technologies can create immersive experiences that redefine entertainment and social interaction. AI-assisted tools can also augment human creativity, helping artists, writers, and musicians generate new ideas, explore novel styles, and produce innovative works. Furthermore, AI-driven platforms can facilitate collaboration, enabling people to co-create and share knowledge, ideas, and experiences across geographical and cultural boundaries. By augmenting human capabilities, AI has the potential to upend traditional norms and unlock new possibilities for personal growth, creative expression, and collective progress. This can lead to a more joyful, creative, and prosperous society.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.