← model directory
meta-llama
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
↓ runs free on your own hardwareLlama 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...
specs & pricing
- Type
- text
- Provider
- meta-llama
- Model ID
- meta-llama/llama-4-maverick
- Capabilities
- vision, tools
- Context window
- 1.0M tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.17 / 1M tokens
- Output price
- $0.66 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.