Back to models
available

Llama 4 Maverick 17B 128E Instruct

meta/llama-4-maverick-17b-128e-instruct-fp8

Prices

Input

$0.25 per 1M tokens

medium
Output

$1.00 per 1M tokens

medium

Also available on

The same model, sold by someone else. The price above is the maker's own.

ChannelWhatPrice
Microsoft AzureInput$0.25 per 1M tokens
Output$1.00 per 1M tokens
IBM watsonx.aiInput$0.371 per 1M tokens
Output$1.48 per 1M tokens
Other · abacusInput$0.14 per 1M tokens
Output$0.59 per 1M tokens
Other · deepinfraInput$0.20 per 1M tokens
Output$0.80 per 1M tokens
Other · huggingface-novitaInput$0.27 per 1M tokens
Output$0.85 per 1M tokens
Other · huggingface-togetherInput$0.27 per 1M tokens
Output$0.85 per 1M tokens
Other · io-netInput$0.15 per 1M tokens
Input (cache write)$0.30 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$0.60 per 1M tokens
Other · novita-aiInput$0.27 per 1M tokens
Output$0.85 per 1M tokens
Other · togetherInput$0.27 per 1M tokens
Output$0.85 per 1M tokens
Other · watsonxInput$0.371 per 1M tokens
Output$1.48 per 1M tokens

Specifications

Provider
meta
Context window
1,000,000
Max output tokens
4,028
Open weights
yes
Released
01/15/2025
Retires
no date announced
First seen by this tracker

Price history

Input — per 1M tokens

1.41009/14/2026today
FromAmount
09/14/20261.41
09/17/20260.25

Output — per 1M tokens

1009/14/2026today
FromAmount
09/14/20260.35
09/17/20261

Last updated 10/01/2026, 02:10