meta-llama
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
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...
- 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
- Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct
- Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct
- Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct
- Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct
- Meta: Llama 4 Scoutmeta-llama/llama-4-scout
- Meta: Llama Guard 4 12Bmeta-llama/llama-guard-4-12b