Claude API pricing and cost calculator
Estimate what the Claude API will cost for your workload, with prompt caching and batch pricing built in.
Prices last verified against official provider pages on . How we verify prices. Written by the Chelure Enterprises Editorial Team.
Claude API prices per million tokens
| Model | Input | Output | 5-min cache write | Cache read |
|---|---|---|---|---|
| Claude Fable 5.2 | $8.00 | $40.00 | $10.00 | $0.20 |
| Claude Fable 5.1 | $10.00 | $50.00 | $12.50 | $0.25 |
| Claude Opus 5.5 | $4.00 | $20.00 | $5.00 | $0.20 |
| Claude Opus 5 | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Sonnet 5.5 | $2.00 | $10.00 | $2.50 | $0.10 |
| Claude Sonnet 5 | $2.00 | $10.00 | $2.50 | $0.20 |
| Claude Sonnet 4.6 | $3.00 | $15.00 | $3.75 | $0.30 |
| Claude Haiku 5.5 (prompts up to 100K tokens) | $0.10 | $0.50 | $0.125 | $0.01 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $1.25 | $0.10 |
Source: Anthropic pricing documentation, verified November 13, 2026. Claude Mythos models are listed by Anthropic as limited availability and are not included.
Things that change a Claude bill
Prompt caching
If every request starts with the same long system prompt or document, you can cache it. Writing it costs slightly more than normal input, and every later read costs a small fraction. For chat applications with a large fixed prompt this is usually the single biggest saving.
Batch processing
Work that does not need an immediate answer, such as classifying a backlog or summarizing archives, can go through the Batch API at half price on both input and output.
The tokenizer
Anthropic notes that Claude 4.7 and later models use a newer tokenizer that produces about 30% more tokens for the same text than Claude Sonnet 4.6 and earlier. When you compare a newer model with an older one, compare cost per task rather than only the per-token price.
Long context
Anthropic lists the full 1M-token context window at standard per-token pricing for Claude 4.6 and later models except Haiku 5.5, so a 900,000-token request is billed at the same per-token rate as a 9,000-token one. Total cost still grows with tokens, so long contexts remain expensive in absolute terms.
Frequently asked questions
How much does the Claude API cost?
Pricing is per million tokens and varies by model. As of November 13, 2026, Claude Sonnet 5.5 is $2 input and $10 output, Claude Opus 5.5 is $4 and $20, and Claude Haiku 5.5 is $0.10 and $0.50 for prompts up to 100,000 tokens.
How much cheaper are cache hits on Claude?
Anthropic bills cache hits at a fraction of the base input price: 0.1x for most models, 0.05x for Claude Opus 5.5 and Sonnet 5.5, and 0.025x for Claude Fable 5.1 and 5.2. Writing to the cache costs more than the base price.
Is there a batch discount for Claude?
Yes. Anthropic's Batch API gives a 50 percent discount on both input and output tokens for asynchronous workloads. Tick the batch box in the calculator to apply it.
Why does Haiku 5.5 have two prices?
Claude Haiku 5.5 is priced differently for prompts up to 100,000 tokens ($0.10 input, $0.50 output) and over 100,000 tokens ($0.50 input, $2.50 output). The calculator uses the lower tier; apply the higher one yourself for very long prompts.
Cite this page: Claude API pricing. Createchz AI Tools, verified November 13, 2026. https://createchz.com/ai-costs/claude-api-pricing/