---
title: "ReportLLMUsage"
method: POST
path: "/gitpod.v1.RunnerInteractionService/ReportLLMUsage"
tags: ["gitpod.v1.RunnerInteractionService"]
---

# ReportLLMUsage

`POST /gitpod.v1.RunnerInteractionService/ReportLLMUsage`

## Request body

- GitpodV1ReportLLMUsageRequest
  - `agentExecutionId` string — The agent execution ID if this usage is associated with an agent execution
  - `diagnostics` GitpodV1LLMUsageDiagnostics — LLMUsageDiagnostics carries content-safe debugging metadata for an LLM request.
    - `codexThreadId` string — Codex IDs are correlation-only values for tracing and debugging.
    - `codexTurnId` string
    - `previousResponseIdPresent` boolean
    - `promptCacheBreakpointCount` integer
    - `promptCacheKeyPresent` boolean — Prompt cache routing and request-shape diagnostics.
    - `promptCacheMode` string — One of default, implicit, or explicit when observed for an OpenAI request.
    - `promptCacheRetention` string
    - `providerRequestId` string — Upstream provider request ID for cross-system correlation.
    - `stablePrefixHash` string
  - `idempotencyKey` string — Idempotency key to prevent duplicate usage reports
  - `llmIntegrationId` string, uuid — The LLM integration's ID
  - `model` string — Upstream provider model slug returned by the provider response. Examples: claude-sonnet-4-5-20250929, gpt-5.3-codex.
  - `runnerId` string, uuid — The runner's identity
  - `supportedModel` 'SUPPORTED_MODEL_UNSPECIFIED' | 'SUPPORTED_MODEL_SONNET_3_5' | 'SUPPORTED_MODEL_SONNET_3_7' | 'SUPPORTED_MODEL_SONNET_3_7_EXTENDED' | 'SUPPORTED_MODEL_SONNET_4' | 'SUPPORTED_MODEL_SONNET_4_EXTENDED' | 'SUPPORTED_MODEL_SONNET_4_5' | 'SUPPORTED_MODEL_SONNET_4_5_EXTENDED' | 'SUPPORTED_MODEL_SONNET_4_6' | 'SUPPORTED_MODEL_SONNET_4_6_EXTENDED' | 'SUPPORTED_MODEL_SONNET_5' | 'SUPPORTED_MODEL_OPUS_4' | 'SUPPORTED_MODEL_OPUS_4_EXTENDED' | 'SUPPORTED_MODEL_OPUS_4_5' | 'SUPPORTED_MODEL_OPUS_4_5_EXTENDED' | 'SUPPORTED_MODEL_OPUS_4_6' | 'SUPPORTED_MODEL_OPUS_4_6_EXTENDED' | 'SUPPORTED_MODEL_OPUS_4_7' | 'SUPPORTED_MODEL_OPUS_4_8' | 'SUPPORTED_MODEL_HAIKU_4_5' | 'SUPPORTED_MODEL_OPENAI_4O' | 'SUPPORTED_MODEL_OPENAI_4O_MINI' | 'SUPPORTED_MODEL_OPENAI_O1' | 'SUPPORTED_MODEL_OPENAI_O1_MINI' | 'SUPPORTED_MODEL_OPENAI_AUTO' — SupportedModel enumerates the LLM models available for agent executions
  - `usage` GitpodV1LLMUsage
    - `cacheInputCreationTokens` string — Number of tokens used for cache input creation
    - `cachedInputTokens` string — Number of cached input tokens used
    - `contextTier` string — Context pricing tier applied to this usage. Defaults to standard when omitted by older runners.
    - `ephemeral1hInputTokens` string — Number of ephemeral 1-hour input tokens used
    - `ephemeral5mInputTokens` string — Number of ephemeral 5-minute input tokens used
    - `inputTokens` string — Number of input tokens consumed
    - `outputTokens` string — Number of output tokens generated
    - `serviceTier` string — Provider service tier applied to this usage. Defaults to default when omitted by older runners.

## Response `200`

Success

- GitpodV1ReportLLMUsageResponse

## Other responses

- `default` — Error

---

[API](https://skmtc.net/gitpod-io/apis/gitpod-v1.md) · [All operations](https://skmtc.net/gitpod-io/apis/gitpod-v1/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/gitpod-io/gitpod-v1/versions/44d50c2ac284/schema)