Vendor pricing
Claude (Anthropic) model pricing
Every Claude (Anthropic) model JP prices, side by side — input, output, and cache rates per million tokens.
| Model | Input (USD / 1M) | Output (USD / 1M) | Cache read (USD / 1M) |
|---|---|---|---|
| Claude Opus 5 | $5.00 | $25.00 | $0.50 |
| Claude Opus 4.8 | $5.00 | $25.00 | $0.50 |
| Claude Opus 4.7 | $5.00 | $25.00 | $0.50 |
| Claude Opus 4.6 | $5.00 | $25.00 | $0.50 |
| Claude Opus 4.5 | $5.00 | $25.00 | $0.50 |
| Claude Fable 5 | $10.00 | $50.00 | $1.00 |
| Claude Mythos 5 | $10.00 | $50.00 | $1.00 |
| Claude Sonnet 5 | $2.00 | $10.00 | $0.20 |
| Claude Sonnet 4.6 | $3.00 | $15.00 | $0.30 |
| Claude Sonnet 4.5 | $3.00 | $15.00 | $0.30 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $0.10 |
Claude Code computes real per-token cost from your local logs at these rates.
How to read this table
All prices are USD per million tokens at published API list rates. Cache reads usually cost less than full input (often about a tenth for Claude/OpenAI/Gemini); where a model shows a >200K tier, crossing that context threshold reprices the whole request.
Tokenizer note
Opus 4.7+, Fable 5, and Sonnet 5 use a newer tokenizer that emits ~30% more tokens for the same text, so the same prompt costs more even at an unchanged rate. Sonnet 4.6 and earlier use the old tokenizer.
Common questions
- Which Claude (Anthropic) model is cheapest?
- The flash / mini / haiku tiers are the lowest per-token; the pro / opus tiers cost more but reason harder. The table shows the exact rates.
Track your real cost with JP the Cat
A live menu-bar total, priced to the cent from your local logs — including the cache-write split most tools miss.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat