AiCostCompare

Llama 4 Maverick

by Meta · meta-llama/llama-4-maverick · #170 cheapest of 457 paid models

Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

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

Pricing

Input

$0.35

per 1M tokens

Output

$1.00

per 1M tokens

Blended (3:1)

$0.512

3 input : 1 output

Cache read

$0.17

per 1M cached tokens

Cache write

—

per 1M tokens

Cache & batch economics

Effective prices for Llama 4 Maverick with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.512$0.0367—
50%$0.445$0.0277−25%
90%$0.391$0.0205−44%

*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$0.000475$0.475
Document summary8,0001,000$0.0038$3.80
Codebase question (RAG)30,0002,000$0.0125$12.50
Long-context analysis150,0005,000$0.0575$57.50

Performance

Intelligence Index

—

AA composite quality

Coding Index

16.3

Math Index

—

Agentic Index

0.6

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Design Arena Elo

CategoryElo
Website862
UI components888
Data viz882
3D881
Game dev827
Code categories868

Specs

Context window

524K

tokens

Max output

33K

tokens

Input modalities

text, image

Tokenizer

Llama4