All Models
Llama-4-Maverick-17B-128E-Instruct-FP8
Open multimodal Llama model for strong reasoning and fast responses
Available Providers (5)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
| | llama-4-maverick-17b-128e-instruct-fp8 | $0/MTok | $0/MTok | 128K | 4.1K | |
| | meta/llama-4-maverick | $0/MTok | $0/MTok | 128K | 4.1K | |
| | llama-4-maverick-17b-128e-instruct-fp8 | $0.25/MTok | $1/MTok | 1M | 16.4K | |
| | llama-4-maverick-17b-128e-instruct-fp8 | $0.25/MTok | $1/MTok | 1M | 16.4K | |
| | meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | $0.37/MTok | $1.48/MTok | 131.1K | 8.2K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output