> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# RunsRunUsageTokens

> Response type in the GraphQL API.

Input excludes cache reads/writes; output includes reasoning. Total is input + output + cache.read + cache.write. Null means unknown, never zero.

| Field | Type | Description |
| - | - | - |
| `input` | [`Float`](https://veryfront.com/docs/cloud/graphql/types/float) | Input tokens excluding cache reads and writes. |
| `output` | [`Float`](https://veryfront.com/docs/cloud/graphql/types/float) | Output tokens including reasoning. |
| `cache` | [`RunsRunUsageTokensCache!`](https://veryfront.com/docs/cloud/graphql/types/runsrunusagetokenscache) | |
| `reasoning` | [`Float`](https://veryfront.com/docs/cloud/graphql/types/float) | Reasoning tokens included in output. |
| `total` | [`Float`](https://veryfront.com/docs/cloud/graphql/types/float) | Sum of input, output, cache-read and cache-write tokens. |

[All GraphQL types](https://veryfront.com/docs/cloud/graphql/schema.md) · [Operations](https://veryfront.com/docs/cloud/graphql.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.