Llama 4 Scout is a Meta model with 10M context, Not verified in / Not verified out per million tokens, last verified October 25, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.
Llama 4 Scout is Meta's open-weight 109B/17B MoE with a 10M-token extended context.
Recorded profile verification October 25, 2026·Individual provider fields may change
Pricing tiers: Llama 4 Community License weights; self-hosting incurs compute costs and hosts set their own prices. Advertised 10M context extends a 256K pre/post-trained window via iRoPE. Meta's current API catalog does not list Llama 4; no first-party token tariff is verified.
Best for
Very long-context retrieval
Open-weight self-hosting
Single-GPU (int4)
Watch out
Custom licence agreement/Notice distribution, attribution, derivative-model naming and acceptable-use terms apply; the 700M-user threshold uses the month before release. Groq's July 17, 2026 Scout shutdown applies to free/developer tiers, with committed-spend enterprise contracts explicitly unaffected. Check the actual host/account. Extended context does not guarantee practical memory or retrieval quality. Hard output cap and effort levels remain unverified. The incorporated AUP withholds Section 1(a) rights for these multimodal weights from EU-domiciled individuals or companies with an EU principal place of business; end users of products/services incorporating the models are excepted. This is a weight-licence condition, not proof of universal regional API unavailability.
Source receipts
Catalog figures for this model were checked against the following sources.
Answered from the verified figures on this page rather than general guidance.
What is Llama 4 Scout's context window?
Llama 4 Scout accepts about 10M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Llama 4 Scout best for?
Llama 4 Scout is a budget tier from Meta. It suits very long-context retrieval, open-weight self-hosting, single-gpu (int4). Custom licence agreement/Notice distribution, attribution, derivative-model naming and acceptable-use terms apply; the 700M-user threshold uses the month before release. Groq's July 17, 2026 Scout shutdown applies to free/developer tiers, with committed-spend enterprise contracts explicitly unaffected. Check the actual host/account. Extended context does not guarantee practical memory or retrieval quality. Hard output cap and effort levels remain unverified. The incorporated AUP withholds Section 1(a) rights for these multimodal weights from EU-domiciled individuals or companies with an EU principal place of business; end users of products/services incorporating the models are excepted. This is a weight-licence condition, not proof of universal regional API unavailability.
Can I self-host Llama 4 Scout?
Llama 4 Scout publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.
