DigitalOcean Gradient™ AI Platform Pricing

Gradient AI Platform has a usage-based pricing model, so costs scale with your actual usage. We charge for model usage (input and output tokens) and for additional features like knowledge bases, guardrails, and log stream insights.

We display prices per million tokens. We charge per thousand tokens for accuracy.

Token usage depends on factors such as the length of user input, complexity of agent instructions, attached knowledge bases, and configuration settings. To optimize usage, test your agents and adjust their parameters.

Open Source Models (Agent Usage)

You are charged for all input and output tokens processed by an agent. Agent creation is free.

Serverless Inference (Direct API Usage)

Serverless inference lets you call models directly through the API without creating an agent.

• For open source models, pricing matches agent usage.

• For commercial models, pricing follows the provider’s published rates:

  • Anthropic’s pricing page
  • OpenAI’s pricing page

All usage is billed per input and output token.

Commercial Models

When using commercial models, billing is handled directly by the provider at the provider’s rates through your API key with them:

• Anthropic’s pricing page
• OpenAI’s pricing page

Knowledge Bases

Knowledge base pricing includes:

• Indexing tokens: You are charged for the tokens required to generate embeddings.

  For example, a 10 MB dataset takes about 3 million tokens, and a 1 GB dataset takes about 250 million tokens.

  Actual costs depend on the embedding model:

  Model	Price
  all-mini-lm-l6-v2	$0.009 per 1,000,000 input tokens
  multi-qa-mpnet-base-dot-v1	$0.009 per 1,000,000 input tokens
  gte-large-en-v1.5	$0.09 per 1,000,000 input tokens

  One token is roughly four characters, or about 75 words per 100 tokens. Non-Latin scripts, emojis, or binary data may increase token counts.

• Storage: Embeddings are stored in OpenSearch. See OpenSearch pricing.

Guardrails

Charges apply for all tokens processed through guardrails:

Costs are per token. Creating, editing, or duplicating guardrails has no additional cost.

Functions

If you attach DigitalOcean Functions to your agent, you are billed at functions pricing.

Agent Evaluations

Agent evaluations are charged by token usage at the same rates as model usage. If you evaluate with a commercial model, billing is handled directly by the provider.

Log Stream Insights

Log stream insights uses a third-party model to analyze agent trace data. You are charged per token: