LV
LLMversus
Meta

Llama 4 Scout

Complete specs, pricing, and benchmark data for Llama 4 Scout by Meta. Last verified 2026-04-03.

VisionMultimodalJSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$0.100

Output / 1M tokens

$0.300

Cached Input / 1M

$0.025

Context & Output

Context Window

10.48576M

Max Output

32,768

TTFT

200ms

Speed

110 tok/s

Benchmarks

Arena ELO

1250

Coding ELO

1230

Reasoning ELO

1220

HumanEval

88

MMLU

85

MATH

72.5

GPQA

53

Price History (Input $/M tokens)

Strengths
  • +10M token context window
  • +Very affordable
  • +Open-source and self-hostable
  • +Good general performance
Limitations
  • -Weaker than Maverick on complex tasks
  • -Requires hosted provider
  • -10M context not supported by all providers

Best For

Long ContextChatbotsCost SensitiveOpen Source

Compare Llama 4 Scout with...

vs o4-minivs Gemini 2.5 Provs Claude Opus 4vs DeepSeek R1vs o3-minivs Grok 3vs GPT-4.1vs Llama 4 Maverickvs Claude Sonnet 4vs DeepSeek V3vs Gemini 2.0 Flashvs GPT-4o
Official Pricing Page →