AI Coding Pricing Data

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

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.

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.

ProviderModelInput / 1MOutput / 1MCache read / 1MCache write / 1MLast updatedSource
AnthropicClaude 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$3.752026-05-24Official
AnthropicClaude Opus 4.6

Estimate only. Opus is usually the high-cost path for long-running agent sessions.

$5$25$0.5$6.252026-05-24Official
OpenAIGPT-5 / GPT-5 Codex

Estimate only. Codex plans, ChatGPT subscriptions and API billing are different billing surfaces.

$1.25$10$0.125$02026-05-24Official
OpenAIGPT-5 mini / Codex mini

Estimate only. Good for bounded coding tasks where cheaper iterations matter more than peak reasoning.

$0.25$2$0.025$02026-05-24Official
GoogleGemini 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$02026-05-24Official
DeepSeekDeepSeek

Estimate only. Promotional rates and model naming can change; verify the pricing page before budgeting.

$0.14$0.28$0.0028$02026-05-24Official

This pricing table is a local estimate for calculator planning. It does not include negotiated discounts, subscription-specific limits, promotional pricing, taxes, currency conversion, or provider-side billing changes after the last updated date.

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.