Devin token usage – Tokenminning

Devin token usage is not one dashboard. Desktop shows quota, credits, or ACUs in Plan Info; cloud shows ACUs per session; enterprise teams pull APIs.

Hub: Tokenminning in Devin.

Where to read the meter

Surface	Location	Units
Devin Desktop	Settings → Plan Info	Quota, on-demand $, ACUs, legacy credits
Self-serve billing	manage your plan	Invoice, cycle reset
Enterprise desktop	Get Consumption API	ACUs by user/model
Devin Cloud	Session Insights, Settings → Consumption	ACUs per session

ACUs vs credits vs quota

Unit	Meaning
ACUs	Agent Compute Units — inference + actions + some VM time (cloud + enterprise desktop)
Legacy credits	Often one credit per user message on premium Cascade models, regardless of tool calls in that turn
Self-serve quota	Included tokens then on-demand rates — see Plans and Usage

Read the column your Plan Info screen actually shows — do not assume ACUs on a credit plan.

Token groups (desktop)

When your plan exposes breakdowns:

Group	High value means
Input	Rules, MCP, index bloat
Cache write	Large first message or tool results
Cache read	Thread too long — new conversation
Output	Thinking models, verbose diffs, loops

Adaptive self-serve rates (through July 7, 2026): ~ $0.50/M input,$ 2.00/M output, $0.10/M cache read — routes simple work to cheaper models underneath.

Enterprise APIs

Devin auth token for metering (not your Git PAT):

Desktop: Get Consumption API , Cascade Analytics API
Cloud: daily consumption , session metrics by category

Rotate API keys on the same schedule as CI secrets.

Cloud vs desktop

Desktop inference bills like other IDE agents. Cloud ACUs add VM time, browser actions, and scoped-task overhead — meter separately.

After a heavy week

Plan Info or Session Insights — which surface moved?
Token group or ACU category — input vs output?
Open the matching spoke: rules, MCP, Devin Local, cloud.