Models/Llama-4-Maverick-17B-128E-Instruct

Llama-4-Maverick-17B-128E-InstructActive · Cloud

Sambanova · Released Apr 2025 · Llama Community License

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Context
131K
Max output
131K
Input
$0.63
Output
$1.80
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Benchmarks

Aider Polyglot15.6

Details

ProviderSambanova
ReleasedApr 2025
LicenseLlama Community License
InputText
OutputText
Throughput-
Availability99.9%

Related models