All Models

Llama 4 Maverick 17B 128E Instruct

llamaTool CallingAttachmentsOpen WeightsStructured Output

Open multimodal Llama model for strong reasoning and fast responses

Providers3
ReleasedJan 15, 2025
Input Modalitiestext, image
Output Modalitiestext
Tarsk Usecoding

Available Providers (3)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Nvidiameta/llama-4-maverick-17b-128e-instruct$0/MTok$0/MTok128K4.1K
IO.NETmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.15/MTok$0.60/MTok430K4.1K
Vertexmeta/llama-4-maverick-17b-128e-instruct-maas$0.35/MTok$1.15/MTok524.3K8.2K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output