API cost calculator

Plan a text-model budget using verified prices and your own token estimates.

Compare up to three models in the same currency. Calculations happen in your browser without an account, API key or model request.

1. Choose models

CurrencyCompare one currency at a time; no exchange-rate conversion.

Select up to 3 modelsclaude-haiku-4-5-20251001Claude APIReview duegemini-2.5-flashGemini Developer APIReview duegemini-2.5-flash-liteGemini Developer APIReview due

2. Describe your usage

Calls per dayNumber of days

Billing scenario

Include billed reasoning/thinking tokens, system instructions and conversation history where applicable. Visible answer length is not the total billable output.

claude-haiku-4-5-20251001

Claude API · Supported regions, Claude API default global routing

Listed as an available legacy model. Check account access and retirement announcements. Continued availability is not guaranteed by this tool.

Input tokens per callBilled output tokens per call

Per-call token limits: 200,000 / 64,000 · Combined input + output: 200,000

Use my own unit prices

Input / 1M tokens (USD)Output / 1M tokens (USD)

Applicable scope

Anthropic first-party API, standard synchronous text-only requests. Excludes cache reads/writes, batch, third-party clouds, tools and taxes. Output must include all billed thinking tokens. Input plus output cannot exceed 200,000 tokens.

Verified: 2026-10-09 · Review by: 2026-10-16

Official pricing ↗ · Model specifications ↗

I have checked the source and accept an estimate with a price awaiting review.

DIGINTOAI / ESTIMATE

Your estimate

Choose a model, adjust your usage and calculate.

API usage is separate from chat subscriptions and Coding Plans.

How the estimate works

Cost = (input tokens × input price + billed output tokens × output price) ÷ 1,000,000 × calls per day × days.

Example: 3,000 input tokens and 1,000 billed output tokens per call, 100 calls per day and 30 days. Change each model's token counts to match its tokenizer and your actual workload.

Token quantities can differ between models. Estimates are not invoices or quality rankings. Taxes, discounts and unsupported billing features are excluded; confirm the provider's current terms.

Your usage and custom prices stay in this browser. A shared link includes those numeric conditions. Anonymous tool-usage totals do not include the entered quantities or prices.

claude-haiku-4-5-20251001 · USD · Verified: 2026-10-09 · Review due

Claude API · Supported regions, Claude API default global routing

Listed as an available legacy model. Check account access and retirement announcements. Continued availability is not guaranteed by this tool.

Input / 1M tokens: 1 USD · Output / 1M tokens: 5 USD

Official pricing ↗ · View model ↗

gemini-2.5-flash · USD · Verified: 2026-10-09 · Review due

Gemini Developer API · Regions supported by Gemini Developer API

Google currently restricts 2.5 access to existing users of these models. New projects must verify availability first. This quote is not a recommendation to purchase or sign up.

Official paid tier, standard synchronous text-only requests. Excludes caching, batch, Flex, priority, audio/video, search and other tools. Output includes all billed thinking tokens.

Input / 1M tokens: 0.30 USD · Output / 1M tokens: 2.50 USD

Official pricing ↗ · View model ↗

gemini-2.5-flash-lite · USD · Verified: 2026-10-09 · Review due

Gemini Developer API · Regions supported by Gemini Developer API

Google currently restricts 2.5 access to existing users of these models. New projects must verify availability first. This quote is not a recommendation to purchase or sign up.

Official paid tier, standard synchronous text-only requests. Excludes caching, batch, Flex, priority, audio/video, search and other tools. Output includes all billed thinking tokens.

Input / 1M tokens: 0.10 USD · Output / 1M tokens: 0.40 USD

Official pricing ↗ · View model ↗