Azure

Llama 4 Maverick 17B 128E Instruct FP8 — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCE
Input Cost
$0.25/1M
Output Cost
$1.0/1M
Context Window
1.0M
Max Output
16K
Knowledge Cutoff
Aug 2024
Accepts
text, image

Llama 4 Maverick 17B 128E Instruct FP8 by Azure demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

Cost Benchmarks

Input Cost
$0.25188th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$1.0197th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
1.0M52nd of 451

Maximum context window size

OpenRouter API

Available from 5 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 2 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Llama$0$0128K
Vercel AI Gateway$0$0128KSupported
Azure$0.25$11.0MSupported
Azure Cognitive Services$0.25$11.0M
watsonx.ai$0.371$1.484131K

Llama 4 Maverick 17B 128E Instruct FP8 — Frequently Asked Questions

How much does Llama 4 Maverick 17B 128E Instruct FP8 cost?

Llama 4 Maverick 17B 128E Instruct FP8 costs $0.25 per 1M input tokens and $1.0 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of Llama 4 Maverick 17B 128E Instruct FP8?

Llama 4 Maverick 17B 128E Instruct FP8 has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Llama 4 Maverick 17B 128E Instruct FP8?

Llama 4 Maverick 17B 128E Instruct FP8 was created by Azure. It is classified as a open source model in our catalogue.

Is Llama 4 Maverick 17B 128E Instruct FP8 open source?

Yes, Llama 4 Maverick 17B 128E Instruct FP8 is an open-source model. The model weights are publicly available for download and self-hosting.