Model developer · Service-channel quotes
DigitalOcean Inference is DigitalOcean’s inference control plane. Serverless inference is billed by DigitalOcean for both open-source and commercial models on a prepaid basis; dedicated inference is billed per GPU-hour and is not a model API price.
Usage-based API, monthly subscriptions and sales quotes are billed differently and are not directly compared; the verified ways to buy are listed below.
Price unverified
Serverless inference is billed by DigitalOcean for both open-source and commercial models on a prepaid basis; DigitalOcean states prices align with each provider’s published rates.
Verified: 2026-11-01 · Official source
Price unverified
Dedicated inference is billed per GPU-hour (for example H100 at $4.41/hour or an 8×H100 node at $30.32/hour). This is compute cost, not a model API token price.
Verified: 2026-11-01 · Official source
No verified public personal monthly subscription at this time; the listings above are the verified usage-based API and the custom / enterprise option. Any future subscription will be added after verification.
Usage-based API, monthly subscriptions and sales quotes are billed differently and are not directly compared; the verified ways to buy are listed below.
价格待核实
Serverless inference is billed by DigitalOcean for both open-source and commercial models on a prepaid basis; DigitalOcean states prices align with each provider’s published rates.
核验: 2026-11-01 · 官方来源
价格待核实
Dedicated inference is billed per GPU-hour (for example H100 at $4.41/hour or an 8×H100 node at $30.32/hour). This is compute cost, not a model API token price.
核验: 2026-11-01 · 官方来源
No verified public personal monthly subscription at this time; the listings above are the verified usage-based API and the custom / enterprise option. Any future subscription will be added after verification.
Distinct model versions are listed once; aliases are not additional models. Prices below are for API usage.
Platform entry for DigitalOcean Inference. It carries no base-model price of its own; model call prices live on the channel offers.