InferClaw Tools

LLM Cost Tool

LLM Model Cost Calculator

Instantly compare what different LLMs cost per token and per million tokens.

Last updated: May 2026

Your Inputs

Official provider pricing

Last verified: 2026-05

GPT-5.5: $5/M input · cache-hit $0.5/M30/M output · 256,000 context

Tokens sent in the prompt (including system prompt, user message, and conversation history).

Tokens returned in the completion.

Results

Input cost per query

$0.5000

100000 tokens × $5.00/M

Output cost per query

$1.50

50000 tokens × $30.00/M

Total cost per query

$2.00

Monthly total cost

$2000.00

1000 queries/month

Cost per 1M input tokens

$5.00

Cost per 1M output tokens

$30.00

Disclaimer:All cost estimates are approximate and based on public API pricing. Actual costs depend on your contract rate, usage patterns, and provider pricing changes. This tool does not constitute financial, legal, tax, or operational advice. Verify pricing with your AI provider's official pricing page.

Assumptions & Limitations

  • Prices are directional and may differ by region, tier, cache usage, router, or enterprise contract.
  • Output token pricing is often 2–10x input token pricing.
  • Rates based on public pricing as of May 2026; providers change pricing without notice.

Frequently Asked Questions

Related Tools