Model Price Index

Updated 2026-08-04 · Changelog

Llama 4 Maverick 17B

AWS Bedrock

Meta's 17B active parameter MoE model with 128 experts on Bedrock, beating GPT-4o across broad benchmarks

$0.24

Input

$0.97

Output

per 1M tokens

Ratesper 1M tokens

Input	$0.24
Output	$0.97

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $33.85/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Specifications

API Model ID	meta.llama4-maverick-17b-instruct-v1:0
Context Window	1M tokens
Max Output	32K tokens

Modalitiestext · image

Capabilitiestool-use · streaming · json-mode · vision · code

More AWS Bedrock Text / Chat Models

Amazon Nova Micro · Amazon Nova Lite · Amazon Nova Pro · Amazon Nova Premier · Claude Opus 4.6 · Claude Sonnet 4.6 · Claude Sonnet 4.5 · Claude Haiku 4.5 · Claude 3.5 Haiku · Llama 4 Scout 17B · Llama 3.3 70B Instruct · Llama 3.1 70B Instruct · Llama 3.1 8B Instruct · Mistral Large 3 · Devstral 2 123B · Pixtral Large · Magistral Small · Ministral 8B · DeepSeek V3.2 · DeepSeek R1 · Claude Opus 4.5 · Claude Opus 4.7 · Claude Opus 4.8 · Claude Fable 5 · Claude Opus 4.1 · Claude Sonnet 4 · Llama 3.2 1B Instruct · Llama 3.2 3B Instruct · Llama 3.2 11B Instruct · Llama 3.2 90B Instruct · Llama 3.1 405B Instruct · Llama 3 8B Instruct · Llama 3 70B Instruct · Mistral 7B Instruct · Mistral Small 24.02 · Command R+ · Command R · Jamba 1.5 Large · Jamba 1.5 Mini · DeepSeek V3.1 · GPT-OSS 20B · GPT-OSS 120B · Qwen3 Coder 30B A3B · Qwen3 32B · Qwen3 235B A22B 2507 · Qwen3 Coder 480B A35B ·