Meta · Llama 4 Scout 17b 16e Instruct · active

Llama-4-Scout-17B-16E-Instruct

Llama-4-Scout-17B-16E-Instruct is an open-weight vision-language model published by Meta.

meta-llama/Llama-4-Scout-17B-16E-Instruct
Statusactive
InputText, Image
OutputText
Context9.5M
Total / active parameters108.6B / 17B
Licenseother
APIYes
Open weights / self-hostYes / Yes

This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.

Provider availability

Serving endpoints and pricing

No directly sourced provider offerings yetPricing and availability stay unknown until collected from each serving provider.

Technical specification

Developer model IDmeta-llama/Llama-4-Scout-17B-16E-Instruct
VersionLlama-4-Scout-17B-16E-Instruct
ReleasedApr 5, 2025
ArchitectureLlama4ForConditionalGeneration
Maximum outputUnknown
Knowledge cutoffNot reported

Capabilities

chatgenerationtools
ReasoningNo
VisionYes
Tool callingYes

Version lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesmeta-llama/Llama-4-Scout-17B-16E-Instruct, meta-llama/Llama-4-Scout-17B-16E-Instruct

Explicit unknowns

  • Maximum output
  • Knowledge cutoff
  • Provider pricing

Comparable peers

Related model comparisons

All comparisons →

Questions

Llama-4-Scout-17B-16E-Instruct FAQs

What is Llama-4-Scout-17B-16E-Instruct?+

Llama-4-Scout-17B-16E-Instruct is an open-weight vision-language model published by Meta. It is developed by Meta and its current sourced lifecycle status is active.

What inputs and outputs does Llama-4-Scout-17B-16E-Instruct support?+

Llama-4-Scout-17B-16E-Instruct's current record lists Text and Image as input and Text as output.

How much context does Llama-4-Scout-17B-16E-Instruct support?+

The current record lists a 10,000,000-token context window and does not report a maximum output length.

Is Llama-4-Scout-17B-16E-Instruct available through an API?+

Llama-4-Scout-17B-16E-Instruct is marked as API-available. No directly sourced serving-provider record is attached yet.

How large is Llama-4-Scout-17B-16E-Instruct?+

The current record lists 108.6B total parameters and 17B active parameters. Its architecture is Llama4ForConditionalGeneration.

What capabilities and tasks does Llama-4-Scout-17B-16E-Instruct support?+

Llama-4-Scout-17B-16E-Instruct's recorded capabilities are chat, generation, and tools. Its supported tasks are image and text.

Can Llama-4-Scout-17B-16E-Instruct be self-hosted?+

Llama-4-Scout-17B-16E-Instruct is an open-weight model. Self-hosting is supported, and the recorded license is other.

Does Llama-4-Scout-17B-16E-Instruct have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are meta-llama/Llama-4-Scout-17B-16E-Instruct.

Which models can Llama-4-Scout-17B-16E-Instruct be compared with?+

The current compatible peer set includes Llama-4-Scout-17B-16E, Llama-4-Maverick-17B-128E, Llama-4-Maverick-17B-128E-Instruct, Mistral-Small-4-119B-2603, and command-a-plus-05-2026-bf16. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons

How current is the Model Markets record for Llama-4-Scout-17B-16E-Instruct?+

Llama-4-Scout-17B-16E-Instruct was last verified Aug 28, 2026 from Meta's primary source, “meta-llama/Llama-4-Scout-17B-16E-Instruct developer model repository.” The evidence is classified as official fact.

Primary evidence

Sources and observation date