Llama

Llama-4-Maverick-17B-128E-Instruct-FP8

Name: Llama-4-Maverick-17B-128E-Instruct-FP8
Brand: Llama

Canonical ID: llama/llama-4-maverick-17b-128e-instruct-fp8

More Llama models More 4-maverick-17b-128e-instruct-fp8 family models

Open multimodal Llama model for strong reasoning and fast responses

Reasoning: No Tool use: Yes Open weights

Overview

text image

Provider: Llama
Family: 4-maverick-17b-128e-instruct-fp8
Release date: 2025-04-05
Last updated: 2025-04-05
Input modalities: text, image
Output modalities: text

Pricing and Limits

Token pricing

Input: $0/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 128,000
Max output tokens: 4,096
Qualified ID: llama/llama-4-maverick-17b-128e-instruct-fp8

Model Summary

Llama-4-Maverick-17B-128E-Instruct-FP8 is a model listing in the Llama provider catalog. It is categorized under the 4-maverick-17b-128e-instruct-fp8 family.

The model supports text, image modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0/1M input and $0/1M output.

Llama-4-Maverick-17B-128E-Instruct-FP8

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Llama

Cerebras-Llama-4-Maverick-17B-128E-Instruct

Cerebras-Llama-4-Scout-17B-16E-Instruct

Groq-Llama-4-Maverick-17B-128E-Instruct

Llama-3.3-70B-Instruct

Llama-3.3-8B-Instruct

Llama-4-Scout-17B-16E-Instruct-FP8