Meta Llama: Llama 4 Scout
meta-llama/llama-4-scout
Access Llama 4 Scout from Meta Llama using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "meta-llama/llama-4-scout"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "meta-llama/llama-4-scout"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="meta-llama/llama-4-scout",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "meta-llama/llama-4-scout",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Llama 4 Scout is Meta's efficient 109 billion parameter MoE model with 17B active parameters and 16 experts, featuring an industry-leading 10M token context window. It fits on a single H100 GPU and handles multimodal text and image inputs.
Context Window 1M
tokens
Max Output 16K
tokens
Input Cost $0.1
per million tokens
Output Cost $0.3
per million tokens
Release Date Apr 5, 2025
Output Speed 98
tokens / sec
Latency 0.63s
time to first token
Model Playground
Try Llama 4 Scout instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Llama 4 Scout performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 58.7% |
| Humanity's Last Exam Cross-domain reasoning | 3.8% |
| LiveCodeBench Recent coding problems | 29.9% |
| SciCode Scientific programming | 17.0% |
| MATH-500 Competition math | 84.4% |
| AIME 2024 Advanced math exam | 28.3% |
| AIME 2025 Advanced math exam | 14.0% |
| IFBench Instruction following | 39.5% |
| LCR Long-context reasoning | 30.3% |
| Terminal-Bench Hard Agentic terminal tasks | 1.5% |
| τ²-Bench Tool use / agents | 15.5% |
Scores sourced from Artificial Analysis.
Find other Meta Llama models →
Muse Glimmer 30B
Muse Glimmer 30B is a 30-billion-parameter dense model from Meta Superintelligence Labs, pairing a causal transformer with a 1.8-billion-parameter vision encoder for text and image input. It's released under an Apache 2.0 license, Meta's first fully open-weight model since Muse Spark moved to a paid API. On Meta's own benchmarks, it scores 76.0 on SWE-Bench Verified, 51.2 on SWE-Bench Pro, 94.7 on AIME 2026, 83.5 on GPQA Diamond, 75.5 on MCP Atlas, and 74.6 on DeepSearch QA, ahead of similarly sized open models like Gemma4 31B and Qwen3.6 27B on Meta's reporting. These figures are vendor-reported and not independently verified. Where Muse Spark targets large-scale multi-agent orchestration, Muse Glimmer sits a size tier down, aimed at tool use, multi-step reasoning, coding, and LLM-as-a-judge evaluation with a 131,072-token context window. It fits developers who want agentic and coding capability at lower cost than the larger Muse Spark models.
ChatMuse Spark 1.1
Muse Spark 1.1 is a multimodal reasoning model from Meta Superintelligence Labs, built for agentic workflows. It accepts text, images, video, audio, and PDF documents as input and returns text, with a 1,048,576-token context window. The model is designed to orchestrate multi-agent workflows, acting as either a main agent that plans and delegates tasks or as a subagent, and it generalizes zero-shot to new tools, MCP servers, and custom skills. It supports parallel function calling, structured output, built-in search with citations, and configurable reasoning effort, and Meta reports strong results on coding across large codebases, computer-use tasks, and visual-to-code generation. This is Meta's first model available through a paid API, priced at $1.25 per million input tokens and $4.25 per million output tokens, aimed at developers building agentic coding tools and enterprise workflow automation.
ChatLlama 4 Maverick
Llama 4 Maverick is Meta's 400 billion total parameter MoE model with 17B active parameters and 128 experts, supporting 1M token context. It's natively multimodal with state-of-the-art performance on coding, reasoning, and image understanding tasks.
Frequently Asked Questions
You can access Llama 4 Scout by Meta Llama through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Llama 4 Scout to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.1 |
| Output | $0.3 |
Llama 4 Scout was created by Meta Llama and released on Apr 5, 2025.
Llama 4 Scout supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,621 pages of text.
Llama 4 Scout can generate up to 16K tokens in a single response.
Llama 4 Scout scores 10.3 on the Artificial Analysis Intelligence Index, outperforming 33% of tracked models. On coding, it scores 8.2 (outperforms 6% of models). On math, it scores 14.0 (outperforms 17% of models).
Yes — the Llama 4 Scout API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add Llama 4 Scout to your app without worrying about API keys or setup.
Read the Docs View Tutorials