ChatLLM
Freemium
Users wanting free multi-model access
Llama 4 Scout
FreeOpen SourceAPISelf-Hosted
Running a capable open-weight model in your own infrastructure sounds straightforward until you discover most options force you to choose between context window depth and multimodal support — Llama 4 Scout and Maverick are Meta's answer to that tradeoff.
Similar tools
ChatLLMFreemiumThe core workflow is model selection plus prompt — pick from the available pool, type, and get…
Claude Sonnet 4.5FreemiumClaude Sonnet 4.5 is a large language model from Anthropic with particular strengths in…
JevProxyFreemiumThe proxy sits in front of your Cursor or Claude Code agent fleet and classifies incoming tool…
CueyFreemiumCuey sits inside your existing ChatGPT, Claude, or Gemini session and routes the same prompt…
Get This Tool
License: License: unverified
Local-run terms: Users may use, reproduce, distribute, modify, and create derivative works of Llama 4 materials for commercial and research purposes, provided: (1) monthly active users do not exceed 700 million; (2) use complies with applicable laws and Meta's Acceptable Use Policy; (3) proper attribution is maintained; (4) output may be used to improve other models if attribution is included.
Screenshots 5
Pricing
- Model
- Free
Summary
Scout carries a 10M token context window, meaning you can feed it an entire codebase or a stack of legal documents in a single pass without chunking pipelines or retrieval hacks. Maverick trades raw context depth for stronger multimodal reasoning, handling interleaved image and text inputs through native early-fusion architecture rather than a bolted-on vision adapter. Both models ship as open weights, downloadable from Hugging Face after license acceptance, with no API bill required if you run them yourself. The ceiling appears at inference: the Mixture-of-Experts architecture demands hardware that most teams do not have sitting idle, and running Scout's full 10M context window in practice requires significant GPU memory that a standard cloud instance will not cover.
Bottom line: Pick Scout when you need to reason over a 500-file repository in a single inference call and you have the GPU budget to match; plan a different stack when your team's inference hardware tops out at what a single A100 can hold.
Hosted & API Pricing
The model is free to self-host. These are the creator's hosted/API options.AWS Bedrock Pay-as-You-Go
via AWS Bedrock
Custom
Fully managed serverless inference for Llama 4 models in US East and US West regions
- Serverless managed service
- Pay-as-you-use pricing
- Multi-region availability
IBM watsonx.ai
via IBM
Custom
Enterprise AI platform offering Llama 4 models with fine-tuning and deployment capabilities
- Fine-tuning support
- Multi-environment deployment
- Enterprise security
Pricing may have changed since last verified. Check the official site for current plans.
LLM Spec Sheet
Benchmarks
131.1k tokensContext Window
Pricing & Limits
- Input price
- $0.11 / 1M tokens
- Output price
- $0.34 / 1M tokens
- Max output tokens
- 8,192
Metrics from vendor, updated .
Find your fit
Before you choose Llama 4 Scout
More options in Multimodal LLMs. Compare pricing, platforms, and features side by side.
Claude Sonnet 4.5
Freemium
Coding and software engineering tasks
Changelog
Pros
- 10M token context window on Scout, so you can pass an entire large codebase or document corpus in a single inference call without building a retrieval pipeline to chunk and re-rank content.
- Native early-fusion multimodality on Maverick, meaning image and text inputs are processed in the same model pass, so you avoid stitching together a separate vision encoder and a language model with a custom integration layer.
- Open weights downloadable at no cost after license acceptance, so your inference bill is your hardware cost alone — no per-token API charges accumulating against a usage cap.
- MoE architecture activates only a subset of parameters per inference pass, which means lower per-token compute cost compared to a dense model at equivalent parameter count, giving your GPU budget more headroom.
- Self-hosted deployment option, so sensitive document content or regulated data never leaves your infrastructure — which closes the door on the data-residency objections that block most SaaS LLM integrations in enterprise procurement.
Cons
- Running Scout's 10M context window at the hardware level requires GPU memory that exceeds a standard single-node cloud instance — teams hitting this wall either partition across multiple nodes with custom serving infrastructure or drop to a shorter effective context, which eliminates the primary reason to choose Scout over smaller models.
- The Llama 4 Community License is not a standard open-source license; it contains commercial use restrictions that legal review at larger enterprises frequently flags, and teams operating at scale or in regulated industries have switched to models carrying Apache 2.0 or MIT licenses specifically to avoid that procurement friction.
- Neither Scout nor Maverick ships with a managed inference API from Meta directly — teams that need guaranteed uptime, autoscaling, and SLA-backed hosting must either build that layer themselves or pay a third-party host, at which point the cost advantage of open weights shrinks against a managed provider like Anthropic or OpenAI.
About
- Platforms
- Linux, macOS, Windows (via HuggingFace, llama.com, Ollama, container environments)
- Languages
- ArabicEnglishFrenchGermanHindiIndonesianItalianPortugueseSpanishTagalogThaiVietnamese
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- June 4, 2026
Best For
Who it's for
- Long-context document analysis and code understanding (Scout)
- High-performance multimodal reasoning and chat (Maverick)
- Organizations needing open-weight models for cost-efficient deployment
- Applications requiring both text and image understanding
What it does well
- Multi-document summarization with 10M context window
- Enterprise chat and visual reasoning with multimodal inputs
- Reasoning over vast codebases and long-term dependencies
- Image and text understanding for customer support applications
- Multilingual content generation and translation
Integrations
Frequently Asked Questions
- Is Llama 4 Scout free?
- Llama 4 Scout offers a free option. Hosting, model usage, or optional services may have separate costs; check the pricing details and official terms.
- Is Llama 4 Scout open source?
- Yes. Llama 4 Scout is open source.
- Does Llama 4 Scout have an API?
- Yes. Llama 4 Scout exposes a developer API. See the official documentation at https://developer.meta.com/ai/ for details.
- Can I self-host Llama 4 Scout?
- Yes. Llama 4 Scout supports self-hosting on your own infrastructure.
- When was Llama 4 Scout released?
- Llama 4 Scout was first released in 2025.
- What platforms does Llama 4 Scout support?
- Llama 4 Scout is available on: Linux, macOS, Windows (via HuggingFace, llama.com, Ollama, container environments).
Curated lists that include this category
Closed-source API lock-in becomes expensive the moment your query volume scales — Llama 4 Scout and Maverick are open-weight models from Meta that let you run frontier-class language and multimodal reasoning on your own hardware. Scout is optimized for long-context tasks, with a 10M token window that allows full-document or full-codebase ingestion without external retrieval. Maverick is positioned for high-performance chat and visual reasoning, accepting both text and image inputs through a Mixture-of-Experts transformer decoder with early fusion, meaning image and text tokens are processed together from the first layer rather than in separate pipelines that merge later.
The architectural differentiator is the MoE design: rather than activating all model parameters on every token, only a subset of expert layers fires per inference pass. The vendor states this makes the models more compute-efficient per token at equivalent parameter counts compared to dense transformers — which matters when you are paying for GPU-hours. Native multimodality through early fusion means Maverick does not need a separate vision encoder pipeline, which reduces the integration surface for teams building customer support or document-processing applications that mix image and text inputs.
These models fit organizations that need cost-efficient deployment at scale, want the weight portability to switch cloud providers or go on-premises, and have engineering capacity to manage their own inference stack. They do not fit teams that need a managed API with guaranteed uptime and SLAs without self-hosting overhead, or teams whose GPU inventory cannot support the memory footprint of a large MoE model — particularly at Scout’s 10M context ceiling. The license is Meta’s Llama 4 Community License, which requires acceptance before download and carries usage restrictions that legal teams at larger organizations will need to review before production deployment.
Weights are available on Hugging Face and llama.com. Third-party API access is available through Meta’s partners for teams that want hosted inference without self-managing hardware, though that path introduces the API cost structure the open-weight release is designed to let you avoid.
Contribute
- Work on Llama 4 Scout? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.