API Reference

Runs

Usage

View as Markdown

View as Markdown

Copy Markdown

---

Open in Claude

Open in ChatGPT

Retrieve Usage For Run

client.runs.usage.retrieve(stringrunID, RequestOptionsoptions?): UsageRetrieveResponse { completion_tokens, completion_tokens_details, prompt_tokens, 2 more }

get/v1/runs/{run_id}/usage

Get usage statistics for a run.

ParametersExpand Collapse

runID: string

ReturnsExpand Collapse

UsageRetrieveResponse { completion_tokens, completion_tokens_details, prompt_tokens, 2 more }

completion_tokens?: number

completion_tokens_details?: CompletionTokensDetails | null

reasoning_tokens?: number | null

prompt_tokens?: number

prompt_tokens_details?: PromptTokensDetails | null

cache_creation_tokens?: number | null

cache_read_tokens?: number | null

cached_tokens?: number | null

total_tokens?: number

Retrieve Usage For Run

TypeScript

• HTTP
• TypeScript
• Python

import Letta from '@letta-ai/letta-client';

const client = new Letta({
  apiKey: 'My API Key',
});

const usage = await client.runs.usage.retrieve('run_id');

console.log(usage.completion_tokens);

200 example

{
  "completion_tokens": 0,
  "completion_tokens_details": {
    "reasoning_tokens": 0
  },
  "prompt_tokens": 0,
  "prompt_tokens_details": {
    "cache_creation_tokens": 0,
    "cache_read_tokens": 0,
    "cached_tokens": 0
  },
  "total_tokens": 0
}

Returns Examples

200 example

{
  "completion_tokens": 0,
  "completion_tokens_details": {
    "reasoning_tokens": 0
  },
  "prompt_tokens": 0,
  "prompt_tokens_details": {
    "cache_creation_tokens": 0,
    "cache_read_tokens": 0,
    "cached_tokens": 0
  },
  "total_tokens": 0
}