losclouds

AI Models / Compare

Llama 4 Scout on Groq

Current Groq-hosted Llama 4 family for better open-model reasoning and tool use.

Creator
Groq
Lifecycle
Active
Context
131.1K
Max output
16.4K
Released
Jun 1, 2025
Status
up
Input
$0.11 / 1M tokens
Output
$0.34 / 1M tokens
Cached read
/ 1M tokens
Cached write
/ 1M tokens
Batch discount
%
Source
Llama 4 Scout on Groq pricing
Verified
Apr 2, 2026 (High)

Capabilities

Modalities
textimagetext
Capabilities
reasoningimageInputbatchSupportpromptCachingfunctionCallingstructuredOutputs
Strengths
Modern open-model tier, Still relatively cheap
Tradeoffs
Open-model ceiling below hosted frontier APIs
Official Links

Benchmark Coverage

BenchmarkVersionScoreDateSourceNotes

Release History

ReleaseAliasLifecycleRelease DateDeprecationShutdownSummary
Llama 4 Scout on Groqgroq-llama-4-scoutActiveJun 1, 2025Current published model family snapshot.

Host Coverage

HostTypeContextPricing NoteDifferences
Groq APIfirst-party131.1KReference production Groq pricing.Image input
Migration Guidance

Open-model upgrade from Llama 3.x tiers for better reasoning and multimodal input.

Replacement models: groq-llama-3-3-70b-versatile

Change Events
DateTypeTitleDescriptionSource
Jun 1, 2025family_addedLlama 4 Scout on Groq publishedInitial public model family launch.Llama 4 Scout on Groq release notes

Other models from Groq

GPT-OSS 120B on Groq, GPT-OSS 20B on Groq, Groq Compound, Llama 3.1 8B Instant on Groq, Llama 3.3 70B Versatile on Groq, Qwen3 32B on Groq