losclouds

AI Models / Compare

Llama 4 Scout

Fast, affordable Llama 4 with 10M context window and image understanding.

Creator
Meta AI
Lifecycle
Active
Context
10.0M
Max output
32.8K
Released
Apr 5, 2025
Status
unknown
Input
$0.11 / 1M tokens
Output
$0.34 / 1M tokens
Cached read
/ 1M tokens
Cached write
/ 1M tokens
Batch discount
%
Source
Llama 4 Scout pricing
Verified
Apr 5, 2026 (High)

Capabilities

Modalities
textimagetext
Capabilities
imageInputbatchSupportpromptCachingfunctionCallingstructuredOutputs
Strengths
10M token context, Very cheap, Open weights
Tradeoffs
MoE architecture, 109B total params but 17B active
Official Links

Benchmark Coverage

BenchmarkVersionScoreDateSourceNotes
MMLU202479.6 %Apr 1, 2025MetaVendor-reported

Release History

ReleaseAliasLifecycleRelease DateDeprecationShutdownSummary
Llama 4 Scoutllama-4-scoutActiveApr 5, 2025Current published model family snapshot.

Host Coverage

HostTypeContextPricing NoteDifferences
Groqcloud131.1K$0.11/$0.34 per MTok.Fast inference
AWS Bedrockcloud10.0M$0.17/$0.60 per MTok.Enterprise integration
Migration Guidance

Primary open-weight fast tier in Llama 4 family.

Change Events
DateTypeTitleDescriptionSource
Apr 5, 2025family_addedLlama 4 Scout publishedInitial public model family launch.Llama 4 Scout release notes

Other models from Meta AI

Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, Llama 3.2 11B Vision, Llama 3.2 90B Vision, Llama 3.3 70B, Llama 4 Maverick