Get Session Cost

const options = {method: 'GET', headers: {'X-Browser-Use-API-Key': '<api-key>'}};

fetch('https://api.browser-use.com/api/v4/sessions/{session_id}/cost', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.browser-use.com/api/v4/sessions/{session_id}/cost"

headers = {"X-Browser-Use-API-Key": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "sessionId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "numRuns": 123,
  "llmCostUsd": "<string>",
  "searchCostUsd": "<string>",
  "browserCostUsd": "<string>",
  "proxyCostUsd": "<string>",
  "proxyUsedMb": "<string>",
  "totalCostUsd": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Sessions

Get Session Cost

Everything this session has cost so far, split by source.

A run’s total_cost_usd is its LLM (and web-search) charge only. Browser time and proxy bandwidth are metered against the session’s browser, which outlives any one run — so this is the endpoint for the session’s full cost.

These are recorded usage costs, not an invoice total: promotional waivers and credits are applied downstream in billing, so a session run under a promotion can report cost here that was never charged.

Costs keep moving after a run reports finished: LLM calls settle up to about 90 seconds later, and the browser accrues time and proxy traffic until it stops.

GET

sessions

{session_id}

cost

Get Session Cost

const options = {method: 'GET', headers: {'X-Browser-Use-API-Key': '<api-key>'}};

fetch('https://api.browser-use.com/api/v4/sessions/{session_id}/cost', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.browser-use.com/api/v4/sessions/{session_id}/cost"

headers = {"X-Browser-Use-API-Key": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "sessionId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "numRuns": 123,
  "llmCostUsd": "<string>",
  "searchCostUsd": "<string>",
  "browserCostUsd": "<string>",
  "proxyCostUsd": "<string>",
  "proxyUsedMb": "<string>",
  "totalCostUsd": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

X-Browser-Use-API-Key

string

header

required

Path Parameters

session_id

string<uuid>

required

Response

Successful Response

Everything a session cost, split by what it was spent on.

Recorded usage, not an invoice total — promotional waivers and credits are applied downstream in billing.

Browser time and proxy bandwidth are metered against the session's browser, which outlives any single run, so they have no per-run number — only RunSummary.total_cost_usd, the LLM (and web search) charge, does.

All amounts are fixed-6-decimal strings for the same reason as RunSummary.total_cost_usd: JS clients lose precision on float.

sessionId

string<uuid>

required

numRuns

integer

required

llmCostUsd

string

required

searchCostUsd

string

required

browserCostUsd

string

required

proxyCostUsd

string

required

proxyUsedMb

string

required

totalCostUsd

string

required

Get Started

Endpoints

Get Session Cost

Authorizations

Path Parameters

Response