AiCostCompare

Llama 4 Scout

by Meta · meta-llama/llama-4-scout · #47 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.10

per 1M tokens

Output

$0.30

per 1M tokens

Blended (3:1)

$0.15

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Llama 4 Scout (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.15$0.0105
50%$0.15$0.0105−0%
90%$0.15$0.0105−0%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.00014$0.14
Document summary8,0001,000$0.0011$1.10
Codebase question (RAG)30,0002,000$0.0036$3.60
Long-context analysis150,0005,000$0.0165$16.50

Performance

Intelligence Index

10

AA composite quality

Coding Index

8.2

Math Index

14

Agentic Index

1.1

Output speed

76 tok/s

median

Time to first token

0.56s

median

Time to first answer

0.56s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro75.2%
GPQA Diamond58.7%
Humanity's Last Exam4.3%
LiveCodeBench29.9%
SciCode17.0%
MATH-50084.4%
AIME28.3%
AIME 202514.0%
IFBench39.5%
AA-LCR (Long Context Reasoning)25.8%
Terminal-Bench Hard1.5%
Terminal-Bench 2.13.7%
τ²-Bench (Telecom)15.5%
τ³-Bench Banking3.3%

Design Arena Elo

CategoryElo
Website778
UI components811
Data viz933
Game dev831
Code categories823

Specs

Context window

1.31M

tokens

Max output

16K

tokens

Input modalities

text, image

Tokenizer

Llama4