Model

Llama 4 Maverick 17B 128E Instruct

3 providers · 3 listingsreleased Apr 29, 2025

$0.15

lowest input /M · IO.NET

$0.6

lowest output /M · IO.NET

524K

context window

max output

Compare providers (sorted by listed input price)

2 of 3 providers publish a price for Llama 4 Maverick 17B 128E Instruct. The cheapest full-context option is Vertex at $0.35/$1.15 per M. IO.NET lists lower but caps context at 430K.

			Cache read /M	Cache write /M		Capabilities
IO.NET meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8	$0.15	$0.6	$0.075	$0.3	430K	no reasoningtoolsno structuredno vision	Jan 15, 2025
Vertex meta/llama-4-maverick-17b-128e-instruct-maas	$0.35	$1.15	—	—	524K	no reasoningtoolsstructuredvision	Apr 29, 2025
Nvidia meta/llama-4-maverick-17b-128e-instruct	—	—	—	—	128K	no reasoningtoolsstructuredvision	Apr 1, 2025

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.15unchanged
Best output /M: $0.6unchanged
Provider coverage: 3; 3 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

![Llama 4 Maverick 17B 128E Instruct price](https://www.vaanalytics.in/badge/llama4maverick17b128einstruct.svg)

https://www.vaanalytics.in/badge/llama4maverick17b128einstruct.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.