Skip to content
CostPerPrompt

Claude Sonnet 4 API Pricing

Anthropic · context window 1M · prices updated 2026-08-02

Input per 1M tokens
$3.00
Output per 1M tokens
$15.00
Cached input per 1M
$0.3
90% cheaper than fresh input

What real workloads cost on Claude Sonnet 4

Workload Per request Per month
1K short requests/day (500 in / 150 out) $0.0037 $113
Support chatbot, 500 convs/day (~5K in / 1.4K out per conv) $0.036 $540
Document pipeline, 10K docs/day (3K in / 500 out) $0.0165 $4950

Model your exact traffic in the API cost calculator — it preloads Claude Sonnet 4 with caching and batch options.

Cheaper alternatives

GPT-5.3 Chat OpenAI $1.75 in · $14.00 out GPT-5.3-Codex OpenAI $1.75 in · $14.00 out GPT-5.2-Codex OpenAI $1.75 in · $14.00 out

More Anthropic models

Claude Opus 4.7 (Fast) Claude Opus 4.1 Claude Opus 4 Claude Opus 5 (Fast)

Frequently asked questions

› How much does the Claude Sonnet 4 API cost?

Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens, with cached input at $0.3 per million (90% cheaper). In practice, a typical short request (500 tokens in, 150 out) costs about $0.0037.

› What does 1,000 requests per day cost on Claude Sonnet 4?

At 500 input + 150 output tokens per request, 1,000 requests/day costs about $113 per month. Heavier workloads scale linearly — use our API cost calculator to model your exact traffic.

› How can I reduce Claude Sonnet 4 costs?

Three levers, in order of impact: (1) route routine requests to a cheaper tier and keep Claude Sonnet 4 for hard cases; (2) enable prompt caching — cached input is 90% cheaper, which typically halves chatbot bills; (3) use the batch API for non-urgent jobs at a ~50% discount.

› Is Claude Sonnet 4 worth the price?

It depends on task difficulty. Flagship models earn their premium on complex reasoning, coding, and high-stakes output; mini/flash tiers handle classification, extraction and routine chat at 10–30× lower cost. Benchmark a sample of your real workload on both before committing.