What will AI actually cost to run in your business?
Paste a prompt, set how often you'll run it, and instantly see the cost across every major model — GPT-4.1, Claude, Gemini, Llama, and more. No guessing.
Costs shown in USD. Based on published API pricing as of May 2026.
←
Your cost breakdown will appear here
Paste a prompt and click Calculate
Cost breakdown
Input tokens
—
Output tokens
—
Cheapest option
—
Cost per call
Model
Input
Output
Total / call
Monthly projection (cheapest vs most capable)
Full model pricing reference
Updated May 2026
Model
Provider
Input (per 1M tokens)
Output (per 1M tokens)
Context window
Best for
GPT-4.1
OpenAI
$2.00
$8.00
1M
Complex reasoning, long docs
GPT-4.1 mini
OpenAI
$0.40
$1.60
1M
High-volume tasks, cost-sensitive
GPT-4.1 nano
OpenAI
$0.10
$0.40
1M
Simple classification, routing
Claude Sonnet 4.6
Anthropic
$3.00
$15.00
200K
Writing, analysis, nuanced tasks
Claude Haiku 4.5
Anthropic
$1.00
$5.00
200K
Fast responses, customer-facing
Claude Opus 4.6
Anthropic
$5.00
$25.00
200K
Most capable, complex workflows
Gemini 2.5 Pro
Google
$1.25
$10.00
1M
Multimodal, long context, coding
Gemini 2.5 Flash
Google
$0.30
$2.50
1M
Speed + quality balance
Gemini 2.5 Flash-Lite
Google
$0.10
$0.40
1M
Cheapest capable model
Llama 4 Scout (via Groq)
Meta / Groq
$0.11
$0.34
328K
Open-source, ultra-low cost
Llama 3.1 8B (via Groq)
Meta / Groq
$0.05
$0.08
128K
Cheapest option, simple tasks
Mistral Large
Mistral
$2.00
$6.00
128K
European data residency, multilingual
Mistral Small
Mistral
$0.10
$0.30
32K
EU compliance, budget tasks
Prices are per 1 million tokens. 1,000 tokens ≈ 750 words. Prices sourced from official provider pricing pages. Groq pricing for hosted inference. Actual costs may vary with caching, batch discounts, or enterprise agreements.