How much does Claude 3.5 Sonnet cost per API call?

Claude 3.5 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens. Claude 3 Haiku is much cheaper at $0.25 input / $1.25 output per million tokens, while Claude 3 Opus is $15 input / $75 output.

Does Anthropic offer prompt caching?

Yes. Anthropic offers prompt caching which lets you cache up to 200K tokens of context. Cache writes cost 1.25× the normal input rate, but cache reads are 90% cheaper — making it valuable for large, repeated system prompts.

How does Claude pricing compare to GPT-4o?

Claude 3.5 Sonnet ($3 input / $15 output) is slightly more expensive for input but cheaper per output token compared to GPT-4o ($2.50 input / $10 output). For high-output tasks, GPT-4o may be more cost-effective.

Claude API Cost Calculator

Calculate Anthropic Claude API costs for Sonnet, Opus, and Haiku.

Model

Input text

0 input tokens detectedOutput estimated at 50% (0 tokens)

Model pricing

Input price$0.000003 / token$3.00 / 1M tokens

Output price$0.000015 / token$15.00 / 1M tokens

Cost estimate

Per request$0.000000

Per 1K requests$0.000000

Daily (100 req)$0.000000

Monthly est.$0.000000

0 input tokens0 output tokens

Related Tools

CLTClaude Token CounterNEW

Count tokens for Claude 3.5 Sonnet, Opus, and Haiku models.

CLDClaude Context Window CalculatorNEW

Calculate token usage against Claude 200K context windows.

CSTAI API Cost CalculatorNEW

Estimate AI API costs for GPT, Claude, Gemini, and LLaMA.

GPTOpenAI API Cost CalculatorNEW

Calculate GPT-4o, GPT-4 Turbo, and GPT-3.5 API costs.

FAQ

How much does Claude 3.5 Sonnet cost per API call?: Claude 3.5 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens. Claude 3 Haiku is much cheaper at $0.25 input / $1.25 output per million tokens, while Claude 3 Opus is $15 input / $75 output.
Does Anthropic offer prompt caching?: Yes. Anthropic offers prompt caching which lets you cache up to 200K tokens of context. Cache writes cost 1.25× the normal input rate, but cache reads are 90% cheaper — making it valuable for large, repeated system prompts.
How does Claude pricing compare to GPT-4o?: Claude 3.5 Sonnet ($3 input / $15 output) is slightly more expensive for input but cheaper per output token compared to GPT-4o ($2.50 input / $10 output). For high-output tasks, GPT-4o may be more cost-effective.

Estimate Anthropic API costs for Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Haiku. Paste text to auto-count tokens or enter counts manually. See per-request and monthly cost breakdowns for your usage patterns.