Anthropic API pricing

Claude Sonnet 4.5 API pricing

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.0 per million output tokens on the Anthropic API, and $0.30 per million cached input tokens. Context window: 200k tokens. Updated .

Price per 1M tokensUS dollars
Input$3.00
Cached input$0.30
Output$15.0

What it costs in practice

  • One chat or extraction call (2,000 tokens in, 500 out): $0.013
  • 1,000 such calls: $13.50
  • 1 million tokens at a typical 80% input / 20% output mix: $5.40

Abilities: image input, tool use, reasoning, JSON schema output. Batch, long-context, priority and regional prices differ; check the full table and the provider’s own pricing page before you commit.

Cheapest alternatives from other providers

ModelInputOutputContextTypical call ×1,000
GPT-5 nano
OpenAI
$0.050$0.40272k$0.30
Gemini 2.5 Flash Lite
Google
$0.10$0.401.0M$0.40
GPT-6 luna
OpenAI
$0.10$0.50922k$0.45
Qwen3.8 Flash
Alibaba (Qwen)
$0.15$0.47992k$0.54
Qwen3.8 Omni Flash
Alibaba (Qwen)
$0.15$0.47992k$0.54
GLM 5.3 Flash
Zhipu (GLM)
$0.15$0.501.0M$0.55

Other Anthropic models

ModelInputOutputContextTypical call ×1,000
Claude Haiku 5.5
Anthropic
$0.10$0.501M$0.45
Claude Haiku 4.5
Anthropic
$1.00$5.00200k$4.50
Claude Sonnet 5
Anthropic
$2.00$10.01M$9.00
Claude Sonnet 5.5
Anthropic
$2.00$10.01M$9.00
Claude Sonnet 4.6
Anthropic
$3.00$15.01M$13.5
Claude Opus 5.5
Anthropic
$4.00$20.01M$18.0

Questions

How much does Claude Sonnet 4.5 cost?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.0 per million output tokens on the Anthropic API; cached input is $0.30 per million. A typical call with 2,000 tokens in and 500 out costs about $0.013.

What is the context window of Claude Sonnet 4.5?

Claude Sonnet 4.5 accepts up to 200,000 input tokens and returns up to 64,000 output tokens.

Is there a cheaper alternative to Claude Sonnet 4.5?

For a typical call, GPT-5 nano (OpenAI, $0.0003 per call), Gemini 2.5 Flash Lite (Google, $0.0004 per call), GPT-6 luna (OpenAI, $0.0004 per call) cost less and also support image input, tool use, reasoning, JSON schema output. Quality differs, so test on your own prompts.

Source: the open LiteLLM model price map (MIT), checked daily (data file).