Home/Models/llama-4-maverick

llama-4-maverick

MetaText + VisionOpen weights · Llama 4 Community

Use with your agent

Context

256K

Input

$0.50/M

Output

$0.80/M

Throughput

140tok/s

Latency

290ms

Popularity

34%

Overview

Llama 4 Maverick is an open mixture-of-experts model built for throughput. Strong out-of-the-box behaviour, fully self-hostable weights, and excellent cost-per-token at scale.

Capabilities

REASONINGStrong multi-step reasoning and planning.

MID CONTEXTBalanced context window for everyday work.

Routing & endpoints

Endpoint	Context	Price	Latency	Status
claws-edge · us-east	256K	$0.50 / $0.80 /M	290ms	Operational
claws-edge · eu-west	256K	$0.50 / $0.80 /M	312ms	Operational
Meta · direct	256K	$0.50 / $0.80 /M	338ms	Operational

Sample request

curl https://api.claws.io/v1/chat/completions \
  -H "Authorization: Bearer $CLAWS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-4-maverick",
    "messages": [{"role": "user", "content": "Hello"}]
  }'