Developer cost model

Claude Code Cost Calculator

Claude Code can burn tokens quickly because it repeatedly reads project context, reasons over diffs and produces patch-oriented output.

No login. No AI API calls. Calculations run locally in your browser.

Last updated: 2026-05-24. Estimate only. This is not a billing statement.

Inputs

AI coding agent cost calculator

Model subscription fees, BYOK API usage, cache reads, cache writes and team workload in one local calculator.

Coding toolPricing modeModelWorkload preset

Tasks per dayAverage turns per taskInput tokens per turnOutput tokens per turnWorking days per monthTeam members

Cache read ratio35%Cache write ratio8%Subscription monthly fee$

Results

No login. No AI API calls. Calculations run locally in your browser.

Anthropic / Claude Sonnet 4.6. Last updated: 2026-05-24

Estimated monthly cost

$73.51

Estimated daily cost

$3.34

Cost per task

$0.67

Estimated yearly cost

$882.11

Token volume

Monthly input tokens

9.90M

Monthly output tokens

1.32M

Monthly cache read tokens

3.46M

Monthly cache write tokens

792.0K

Cost risk level

Medium

Main cost driver: input context

Suggested ways to reduce cost

Keep task context bounded so input tokens do not grow silently.
Use explicit task boundaries before starting an agent run.
Prefer patch-oriented output over broad explanations.
Review high-cost sessions and reuse successful prompts.

TokenPatch

Want to measure cost per applied patch instead of raw token usage? Try TokenPatch.

TokenPatch TokenPatch GitHub

Workflow assumptions

Claude Code can burn tokens quickly because it repeatedly reads project context, reasons over diffs and produces patch-oriented output.

Use this calculator for API, subscription and Max plan planning. Actual plan enforcement and rate limits can differ.

API mode maps most directly to model token pricing.

Subscription and Max plan estimates should be treated as capacity planning, not exact billing.

Long project context, repeated file reads and test output are usually the main token drivers.

TokenPatch

Want to measure cost per applied patch instead of raw token usage? Try TokenPatch.

TokenPatch TokenPatch GitHub

Pricing data

Model price assumptions

Pricing data is stored locally in the site configuration and should be treated as a planning estimate. Verify official provider pages before budgeting.

Provider	Model	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M	Last updated	Source
Anthropic	Claude Sonnet 4.6 Estimate only. Claude Code plan limits, Max plan behavior and enterprise contracts can differ from API token pricing.	$3	$15	$0.3	$3.75	2026-05-24	Official
Anthropic	Claude Opus 4.6 Estimate only. Opus is usually the high-cost path for long-running agent sessions.	$5	$25	$0.5	$6.25	2026-05-24	Official
OpenAI	GPT-5 / GPT-5 Codex Estimate only. Codex plans, ChatGPT subscriptions and API billing are different billing surfaces.	$1.25	$10	$0.125	$0	2026-05-24	Official
OpenAI	GPT-5 mini / Codex mini Estimate only. Good for bounded coding tasks where cheaper iterations matter more than peak reasoning.	$0.25	$2	$0.025	$0	2026-05-24	Official
Google	Gemini Pro Uses Gemini Pro-class paid-tier pricing for prompts at or below 200k tokens. Long context pricing can be higher.	$2	$12	$0.2	$0	2026-05-24	Official
DeepSeek	DeepSeek Estimate only. Promotional rates and model naming can change; verify the pricing page before budgeting.	$0.14	$0.28	$0.0028	$0	2026-05-24	Official

FAQ

Is this an exact bill predictor?

No. It is an estimate for AI coding workflows. Provider billing, subscriptions, discounts and limits can vary.

Does the calculator call an AI API?

No. All calculations run locally in your browser and no login is required.

Why do coding agents use more tokens than chat?

They repeatedly consume repository context, command output, diffs, plans and review feedback across many turns.