Cost calculators for AI builders
Token counting is easy.
Real cost modeling is not.
Estimate what AI coding tools actually cost. Start with the Claude Code plan verdict: paste one month of real usage and see whether Pro, Max, or the API wins. More tools below for caching, batch, and agent-loop cost.
Frontier model pricing
All models →- Claude Fable 5 $10.00 / $50.00
- Claude Opus 4.8 $5.00 / $25.00
- GPT-5.5 $5.00 / $30.00
- Gemini 3.1 Pro (Preview) $2.00 / $12.00
- Llama 4 Scout (Groq) $0.11 / $0.34
Input then output, USD per 1M tokens. Cache, batch, and long-context tiers are on the individual model pages. All models verified. Last refresh 2026-06-12.
Paste one month of real usage (ccusage output) and get the API-equivalent bill, your value multiple, and a verdict on Pro vs Max vs API. Plus a receipt card you can drop in the group chat. Parsed in your browser, never uploaded.
Quick token counter
Full counter →Cost estimate assumes 1,000 calls of this prompt as input plus 200 output tokens per call. Tokenizer for non-OpenAI models is approximated with cl100k_base or char/4, typically within 5 to 15% of true count. Claude models from Opus 4.7 onward (including Fable 5) use a newer tokenizer that produces roughly 30% more tokens for the same text, so counts for those models may run low. Pricing data last verified 2026-06-12.
What's different here
Most calculators stop at headline pricing. We model what actually drives the bill.
- 01
Caching ROI, not hand-waving
Anthropic's prompt cache cuts repeat input by up to 90%. Most calculators stop at the headline number. We model cache write cost against read cost against hit rate, and tell you the break-even point where caching actually pays.
Caching ROI - 02
Sync vs batch vs flex, decided
Batch is 50% off, but only fits async workloads. We frame this as a workload decision, not just a discount, so you know when to use batch and when not to.
Batch decision tool - 03
Agent loops, real cost
Multi-turn agents with tool calls, reasoning tokens, retries, and context growth cost very differently from single API calls. Project realistic monthly spend with workload templates for chatbots, coding agents, RAG, and batch classifiers.
Agent simulator - 04
Always current, transparently
Every model carries a last-verified stamp and an official-vs-inferred confidence flag. We publish a changelog. There's a "report incorrect price" link in the footer.
Changelog
More narrow calculators (Cursor, Aider, Cline, agent-API workflows) ship only when the Claude Code verdict tool proves people want them. One tool, one decision, no marketing fluff.
Ready when you are
Stop guessing. Model the bill.
Start with the Claude Code verdict tool if you're deciding between Pro, Max, or API. Or jump into the agent simulator for any other LLM workflow.