Llama 4 Maverick
OnlineFrontierOpen sourceMeta · Meta
meta/llama-4-maverick
Meta open-weight workhorse for private deployments and high-throughput apps.
Meta open-weight workhorse for private deployments and high-throughput apps.
General assistant with strong multilingual support. A default for teams that prefer open weights.
Weights and inference stay on the host. Cautus Intelligence meters the gateway; buyers never receive the raw endpoint credentials.
Provider-hosted capacity
Last heartbeat 10/11/2026, 4:19:10 PM
Frontier or open weights listed for unified billing; compute remains with the provider.
Lineage a buyer can click: base weights, license, fine-tune story, region, and custody. We do not invent eval scores. If no third-party card exists, the listing says so and still pins a card hash.
General assistant with strong multilingual support. A default for teams that prefer open weights.
Mode: Open API
Open marketplace access. Usage metered per token and settled on Litheum.
No approval queue. Sign in for credits, create an mg_ key, and call this slug. Competitor domain blocks still apply if the host configured them.
This call → usage tx → settlement tx on Litheum. Platform take on this listing is 2.5% (BYO compute). Remainder goes to the model owner and, on matched jobs, the compute provider. Example at $0.15 / $0.6 per 1M: a 1M in + 1M out call costs $0.7500.
Open Litheum explorer