Amazon Bedrock

Llama 4 Maverick 17B Instruct (US) — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCE
Input Cost
$0.24/1M
Output Cost
$0.97/1M
Context Window
1.0M
Max Output
8K
Knowledge Cutoff
Aug 2024
Accepts
text, image

Llama 4 Maverick 17B Instruct (US) by Amazon Bedrock 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
$0.24187th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$0.97195th 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 6 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 1 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Abacus$0.14$0.591.0M
Amazon Bedrock$0.24$0.971.0MSupported
Charm Hyper$0.255$0.8365$0.1275430K
DevPass (LLM Gateway)$0.27$0.851.0M
LLM Gateway$0.27$0.851.0M
Neon$0.5$1.51.0M

Llama 4 Maverick 17B Instruct (US) — Frequently Asked Questions

How much does Llama 4 Maverick 17B Instruct (US) cost?

Llama 4 Maverick 17B Instruct (US) costs $0.24 per 1M input tokens and $0.97 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of Llama 4 Maverick 17B Instruct (US)?

Llama 4 Maverick 17B Instruct (US) 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 Instruct (US)?

Llama 4 Maverick 17B Instruct (US) was created by Amazon Bedrock. It is classified as a open source model in our catalogue.

Is Llama 4 Maverick 17B Instruct (US) open source?

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