Skip to content
Free
ModelsMetaopen weights6 providers

Llama 4 Maverick 17B Instruct (AWS Bedrock)

Open multimodal Llama for strong reasoning with efficient everyday serving

Best input price

$0.14

per million tokens

Context window
1,048,576

tokens

Reasoning
No
Tool calling
No
Released
2025-04-05

Inference providers6 hosting Llama 4 Maverick 17B Instruct (AWS Bedrock)

  • Abacus

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

    1,048,576 context$0.59 out / 1M
    $0.14

    in / 1M

    Docs

  • LLM Gateway

    aws-bedrock/llama-4-maverick-17b-instruct

    8,192 context$0.97 out / 1M
    $0.24

    in / 1M

    Docs

  • Amazon Bedrock

    us.meta.llama4-maverick-17b-instruct-v1:0

    1,000,000 context$0.97 out / 1M
    $0.24

    in / 1M

    Docs

  • watsonx.ai

    meta-llama/llama-4-maverick-17b-128e-instruct-fp8

    131,072 context$1.48 out / 1M
    $0.37

    in / 1M

    Docs

  • Neon

    llama-4-maverick

    1,000,000 context$1.50 out / 1M
    $0.50

    in / 1M

    Docs

  • OCI Generative AI

    meta.llama-4-maverick-17b-128e-instruct-fp8

    512,000 context$0.72 out / 1M
    $0.72

    in / 1M

    Docs