Quick facts

Model ID meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Source Deep Infra

Context Window 1048576

Pricing $0.15 input / $0.60 output per 1M tokens

Capabilities open weights

Model overview

Llama 4 Maverick 17B FP8 is an AI model from Deep Infra with 1048576 token context window and text, image input support.

Published pricing is $0.15 input and $0.60 output per 1M tokens.

Model ID meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Provider Deep Infra

Family llama

Status -

Knowledge Cutoff -

Release Date 2025-04-05

Input Modalities text, image

Output Modalities text

Context Window 1048576

Input Limit -

Output Limit 16384

Tool Calling No

Reasoning No

Structured Output -

Temperature Control -

Open Weights Yes

Input Cost / 1M tokens $0.15

Output Cost / 1M tokens $0.60

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -