Ocean Network Launches ‘Inference’ AI Service With Hourly GPU Billing

Ocean Network, a decentralized GPU cloud platform, has launched Inference, an AI inference service that allows users to keep AI models deployed continuously in dedicated GPU environments.

Cointelegraph reported on September 10 that Ocean Network officially unveiled the Inference service. Users can continuously deploy AI models and applications on dedicated GPU nodes accessible via HTTP. The company described the launch as its biggest feature expansion since the platform debuted.

Ocean Network said the existing AI infrastructure market is hampered by opaque pricing, limited model transparency and uncertainty over hardware allocation. Inference is designed to address those issues by showing estimated costs before a session begins and charging by GPU usage time rather than token consumption. Each request is routed to a dedicated node instead of shared infrastructure.

Pricing starts at $2.16 an hour for an H200 GPU. In internal tests, the service generated a 30-second video in about 20 minutes at a cost of $0.72. Payments are processed on-chain through an escrow contract on the Base blockchain.

The service is available in four formats: curated models, custom models, services and templates. Curated models include preconfigured options such as Qwen3-8B, while custom models support models listed on the Hugging Face Hub. To mark the launch, Ocean Network is also offering free credits equal to six hours of H200 GPU usage.