ModelRefs / Llama 4 Scout by Meta — Benchmarks, Pricing & Review (2026)

Llama 4 Scout by Meta — Benchmarks, Pricing & Review (2026)

Llama 4 Scout (Meta): Llama 4 Scout is Meta's efficiency-focused open-weights model with an exceptionally large 10M-token context window and vision support.…

What this reference supports

Llama 4 Scout is the smaller Llama 4 release: a natively multimodal mixture-of-experts model with 17B active parameters across 16 experts, published as open weights with a Meta-reported multi-million-token context window. Validating long-context behavior on the actual serving stack is the central implementation decision.

Llama 4 Scout is attributed to Meta in ModelRefs' canonical registry. Tracked modalities: Text input and output, Image input. Primary use cases considered on ModelRefs: Long-input document and codebase analysis on self-managed infrastructure; Cost-conscious open-weight multimodal assistants and extraction pipelines.

This ModelRefs profile is Provisional and pending review — decision-support material, not a final or universal ranking. Confirm current behavior, access, pricing, limits, licensing, and lifecycle in Meta's own documentation, and evaluate Llama 4 Scout on representative workloads before implementation.

Benchmark & Evaluation

ModelRefs currently has partial, narrow benchmark coverage for Llama 4 Scout. Treat the available benchmark evidence as one input to the decision, not a guarantee that Llama 4 Scout is the strongest option for your workload, and evaluate it on representative workloads before selecting it.

  • No benchmark score is imported into this editorial record. Provider-reported evaluations support scoped notes only; canonical score records are governed separately with their own provenance.
  • Meta's release blog and the model card report provider-run evaluations; long-context claims in particular require deployment-specific validation.

Implementation considerations

  • Treat the extreme context-window figure as Meta-reported: measure retrieval quality, latency, and memory at the depths you will actually use, on your runtime.
  • Choose quantization and expert-parallelism settings deliberately; they change quality and throughput more than family-level claims suggest.
  • Model artifacts are distributed for licensed deployment via Meta and Hugging Face.
  • Hosted Scout endpoints frequently cap context below the release-claimed maximum; verify the effective limit per host.

Risks and limitations

  • Open-weight results depend on the exact runtime, precision, quantization, and prompt template; reference results do not transfer automatically.
  • The release-specific license and acceptable-use policy must be reviewed before commercial deployment.

Source coverage

This reference is Provisional. Model behavior, access, pricing, limits, and lifecycle can change; verify the linked provider documentation and run task-specific evaluations before implementation.

Known coverage gaps:

  • Independent long-context evaluations at production depths are not attached.
  • Host-by-host effective context and quantization mapping is incomplete.

Sources

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Llama 4 Scout by Meta — Benchmarks, Pricing & Review (2026).