Skip to main content

LLMTokenUsage

API reference

A count of tokens consumed by LLM API calls.

Implements Node

cachedTokenReads: Int!

Input tokens served from the provider's prompt cache.

cachedTokenWrites: Int!

Input tokens written to the provider's prompt cache.

id: ID!

A unique identifier for this LLMTokenUsage.

inputTokens: Int!

Uncached input tokens sent to the model.

outputTokens: Int!

Tokens received from the model, including text and tool calls.

totalTokens: Int!

Total tokens consumed, as reported by the provider.

References

Returned by