Mycelis
Products Model hosting BYOK & Managed Keys Agents & Smart Routing Fine-Tuning (LoRA) Knowledge Bases & RAG MCP Tools API Gateway
Use Cases Compliance & Privacy Team rollout Cost Control Quick start with managed keys Your own assistants Fine-tuning with domain knowledge OpenClaw / OpenCode MCP Integration OpenAI compatibility
Resources Getting Started Documentation Blog Status
Models MCP Hub Pricing FAQ
EN DE
Get started Login

Meta

Llama 4 Maverick 17B MoE

Llama 4 Maverick 17B MoE is an open-source model from Meta. Focus areas: Enterprise, Coding, Vision, Reasoning. Context window: 1,000,000 tokens.

Open sourceEnterpriseCodingVisionReasoningLong Context
Deploy this model View on Hugging Face

Context window

1M

Reasoning level

8 / 10

MMLU

86.0

HumanEval

85.0

Recommended deployment

GPU

B200

VRAM required

160 GB

Estimated cost

$10.43 / hour

Estimated from current GPU pricing, billed per hour while the deployment runs and stopped automatically when idle. The exact price depends on live GPU availability at deploy time.