Pick a model — we supply the price. Model prices below were checked October 27, 2026. Enter your monthly usage and your human review time, and get the real monthly cost. The tool subscription is usually the small part; review time is where agent workflows really cost money. Everything runs in your browser, nothing uploaded. For agents specifically — subscriptions, credits, hosting, and your maintenance time added up — see The Real Cost of an AI Agent.
1. Pick a model
2. Your monthly usage
3. Human review time
Prices we found — checked October 27, 2026
Standard tier, USD per 1M tokens, from the vendors' published pricing. These are the exact prices the calculator above uses. Prices change — verify on the official pricing page before budgeting.
Model
Input / 1M
Output / 1M
Note
GPT-6 Astra (OpenAI)
$10.00
$50.00
GPT-6.1 Sol (OpenAI)
$2.00
$10.00
GPT-6.1 Terra (OpenAI)
$1.00
$5.00
GPT-6 Luna (OpenAI)
$0.10
$0.50
Claude Fable 5.1 (Anthropic)
$10.00
$50.00
Claude Opus 5.5 (Anthropic)
$4.00
$20.00
Claude Sonnet 5.5 (Anthropic)
$2.00
$10.00
Claude Haiku 5.5 (Anthropic)
$0.10
$0.50
Prompts over 100,000 tokens: $0.50 / $2.50
Gemini 4 Argon (Google)
$2.00
$10.00
Introductory until Nov 30, 2026 — $4.00 / $20.00 from Dec 1, 2026
Gemini 3.8 Flash (Google)
$0.75
$3.75
Introductory until Dec 31, 2026 — $1.50 / $7.50 from Jan 1, 2027
DeepSeek V4 Pro
$0.66
$1.98
Off-peak; peak hours double both rates
DeepSeek V4.1 Flash
$0.15
$0.60
Off-peak; peak hours double both rates
Newest-first orders models within each company by launch date (Fable 5.1's launch date has not been published in the sources we checked, so it sits last in its family). Strongest-first is by tier — flagship, workhorse, mid-range, budget — and is approximate across vendors, since strength isn't a single measured number.
Estimate only. Model prices are standard-tier API list prices in USD per 1M tokens, compiled October 27, 2026 from the vendors' published pricing — prices change, so verify on the official pricing page before budgeting. Assumptions are shown in the result so you can challenge them: API cost = input tokens ÷ 1M × input price + output tokens ÷ 1M × output price; review hours = tasks × minutes ÷ 60; review cost = review hours × hourly rate; total = API cost + review cost; cost per task = total ÷ tasks. Batch, caching, and peak/off-peak discounts are not included unless noted on the model. If review time drops to zero, ask what happens when the agent gets something wrong unchecked.