Claude API Pricing
Compare input and output token prices across AI language models.
| Provider | Model | Input per 1M tokens | Output per 1M tokens | |
|---|---|---|---|---|
Anthropic | Claude Haiku 5.5 | $0.10 | $0.50 | View |
Anthropic | Claude Haiku 4.5 | $1.00 | $5.00 | View |
Anthropic | Claude Sonnet 5.5 | $2.00 | $10.00 | View |
Anthropic | Claude Sonnet 5 | $2.00 | $10.00 | View |
Anthropic | Claude Sonnet 4.5 | $3.00 | $15.00 | View |
Anthropic | Claude Sonnet 4.6 | $3.00 | $15.00 | View |
Anthropic | Claude Opus 5.5 | $4.00 | $20.00 | View |
Anthropic | Claude Opus 4.5 | $5.00 | $25.00 | View |
Anthropic | Claude Opus 4.6 | $5.00 | $25.00 | View |
Anthropic | Claude Opus 5 | $5.00 | $25.00 | View |
Anthropic | Claude Opus 4.7 | $5.00 | $25.00 | View |
Anthropic | Claude Opus 4.8 | $5.00 | $25.00 | View |
Anthropic | Claude Fable 5.2 | $8.00 | $40.00 | View |
Anthropic | Claude Fable 5.1 | $10.00 | $50.00 | View |
Anthropic | Claude Fable 5 | $10.00 | $50.00 | View |
Anthropic API cost calculator
Enter the tokens of a typical request to compare what it costs with every model in the table. Not sure how many tokens your prompt has? Paste it into the token calculator.
| Model | Per request | Per month |
|---|---|---|
| Claude Haiku 5.5 | $0.00045 | $4.50 |
| Claude Haiku 4.5 | $0.0045 | $45.00 |
| Claude Sonnet 5 | $0.009 | $90.00 |
| Claude Sonnet 5.5 | $0.009 | $90.00 |
| Claude Sonnet 4.5 | $0.01 | $135.00 |
| Claude Sonnet 4.6 | $0.01 | $135.00 |
| Claude Opus 5.5 | $0.02 | $180.00 |
| Claude Opus 4.5 | $0.02 | $225.00 |
| Claude Opus 4.6 | $0.02 | $225.00 |
| Claude Opus 4.7 | $0.02 | $225.00 |
How Claude API pricing works
Anthropic bills the Claude API per token, with separate prices for input tokens (your prompt, documents, and images) and output tokens (the generated answer). Prices in the table are standard rates per 1 million tokens.
Claude models come in tiers: Haiku is the fastest and cheapest, Sonnet balances price and capability, and Opus and the newer top tier models are the most capable and the most expensive. Start with the cheapest tier that handles your task and move up only where quality requires it.
Anthropic also discounts batch requests and cached prompt tokens, which helps with long system prompts and offline workloads; the table shows standard on-demand prices.
FAQ
How much does the Anthropic API cost?
As of November 17, 2026, Anthropic charges from $0.10 to $10.00 per 1M input tokens and from $0.50 to $50.00 per 1M output tokens across the 15 models in the table above.
What is the cheapest Anthropic model?
Claude Haiku 5.5, at $0.10 per 1M input tokens and $0.50 per 1M output tokens. A request with 2,000 input and 500 output tokens costs about $0.00045 with it, so 1,000 such requests cost $0.45.
What is the most expensive Anthropic model?
Claude Fable 5.1, at $10.00 per 1M input tokens and $50.00 per 1M output tokens. The same 2,000 input and 500 output token request costs about $0.05, so pick the smallest model that handles your task well.
Which Anthropic model has the largest context window?
Claude Haiku 5.5 accepts up to 1M tokens of context. Long prompts are billed as input tokens, so filling the whole window costs about $0.10 per request.
Is Anthropic cheaper than other LLM APIs?
Not at the low end: Qwen3.7-Flash costs $0.03 per 1M input tokens and $0.13 per 1M output tokens, less than any Anthropic model. Price is only part of the choice, so compare quality and context window as well in the LLM price comparison.
How do I estimate the cost of my prompts?
Count the tokens of a typical prompt and answer with the token calculator, then enter them in the cost calculator above to see the price per request and per month for every Anthropic model.
