← model directory

meta-llama

Meta: Llama 4 Maverick

meta-llama/llama-4-maverick

↓ runs free on your own hardware⚙ tool calling

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...

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
$0.21 / 1M tokens
Output price
$0.72 / 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.

What it costs to run

cloud · 1M in + 1M out

$0.92

$0.21 for a million input tokens plus $0.72 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

Run it on your own hardware

Estimated GPU memory for Meta: Llama 4 Maverick (402B parameters), including the KV cache for a 8,192-token context.

Q4_K_M
~230.4 GBmulti-GPU or large unified memory
Q8_0
~398.7 GBmulti-GPU or large unified memory
FP16 / BF16
~750.3 GBmulti-GPU or large unified memory

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

/// initialize

Call Meta: Llama 4 Maverick through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Meta: Llama 4 Maverick?
Meta: Llama 4 Maverick accepts up to 1,048,576 tokens (1.0M) of context per request.
How much does Meta: Llama 4 Maverick cost per million tokens?
Through Wide Area Intelligence, Meta: Llama 4 Maverick costs $0.21 per 1M input tokens and $0.72 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.92.
Can I run Meta: Llama 4 Maverick on my own hardware?
Yes — Meta: Llama 4 Maverick is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 230.4 GB of GPU memory with an 8,192-token context — more than a single 80 GB card, so plan for multiple GPUs or a large unified-memory machine. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from meta-llama

← browse all models