Free developer tool
AI Model API Cost Calculator
Estimate Claude API token costs before you build. Choose a model, enter input and output tokens and how many calls you plan, and get the per-call and total cost from official published rates.
Usage
model id: claude-sonnet-5-5
Estimated cost
Claude Sonnet 5.5 · per call
$12.00
- Input cost
- $2.00
- Output cost
- $10.00
Total for 1 call
$12.00
Estimates use official base standard rates (USD per million tokens). Prompt caching, batch discounts, long-context premium tiers, and priority tiers are not included.
Compare all models for this usage
| Model | Model ID | $/MTok in | $/MTok out | Per call | Total |
|---|---|---|---|---|---|
| Claude Fable 5.1 | claude-fable-5-1 | $10.00 | $50.00 | $60.00 | $60.00 |
| Claude Opus 5.5 | claude-opus-5-5 | $4.00 | $20.00 | $24.00 | $24.00 |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | $2.00 | $10.00 | $12.00 | $12.00 |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | $1.00 | $5.00 | $6.00 | $6.00 |
This tool estimates third-party Claude API token costs only. It is not a quote for ChatGPT or Claude subscription plans, and it is not related to the pricing of this website, which is free to use.
It does not call any AI provider and stores nothing. Rates are the official base standard rates published by Anthropic, verified 2026-09-30. Prompt caching, batch discounts, long-context premium tiers, and priority tiers are not included and may change the real cost. Always confirm current rates at the official sources:
The models above are Anthropic's current-generation lineup (including Claude Sonnet 5.5 and Claude Opus 5.5) as of 2026-09-30. This page will be updated when Anthropic publishes new models or rates.
How to Estimate Your API Cost
- 1
Pick a model
Choose from the official Claude lineup with its published per-million-token rates.
- 2
Enter your usage
Type input and output tokens per call (raw, thousands, or millions) and the number of calls.
- 3
Read the estimate
See the per-call and total cost, then compare every model side by side for the same usage.
Claude API Rates at a Glance
The biggest cost driver is output volume: at official standard rates, output tokens cost five times as much as input tokens across the current lineup. A call with one million input tokens and one million output tokens costs $12 on Sonnet 5.5 ($2 in + $10 out) and $24 on Opus 5.5 ($4 in + $20 out), so the same workload is twice as cheap on Sonnet. Batch processing halves these rates and prompt caching can cut repeated input costs substantially, but neither is included in the estimates above—always confirm current rates at the official sources shown with the calculator.
From Cost Estimate to Prompt Workflow
Planning a Claude-powered creative workflow? This site's free AI image description generator turns a photo into an English scene description, and the image-to-video prompt library shows how to turn that description into motion. Use this calculator to budget the API calls behind such pipelines.
Frequently Asked Questions
How is the API cost calculated?
Cost = (input tokens ÷ 1,000,000 × input rate + output tokens ÷ 1,000,000 × output rate) × number of calls. The rates are the official Anthropic base standard rates in USD per million tokens, verified 2026-09-30.
Which models are included, and why no legacy models?
The calculator lists Anthropic’s current-generation lineup as of 2026-09-30: Claude Fable 5.1, Opus 5.5, Sonnet 5.5, and Haiku 4.5, with their official model IDs. Older legacy models are not listed because their current rates were not re-verified at the data date; the same usage can be compared across all included models side by side.
Does this include prompt caching, batch pricing, or long-context rates?
No. The calculator uses base standard rates only. Prompt caching, batch discounts, long-context premium tiers, and priority tiers are not included, so the real bill can be lower or higher than this estimate.
Is this the price of a Claude subscription?
No. The estimates are third-party developer API token costs. They are not Claude or ChatGPT subscription fees, and this website is free to use—these costs are not related to this site.
Does this tool call the AI models or store my inputs?
No. The calculator runs entirely in your browser with published rates. It never calls a model API, and nothing you type is sent to a server or stored.
What are the current official Claude API rates?
Verified 2026-09-30 from platform.claude.com: Fable 5.1 costs $10 per million input tokens and $50 per million output tokens; Opus 5.5 costs $4/$20; Sonnet 5.5 costs $2/$10; Haiku 4.5 costs $1/$5.