TokenTally

Claude Haiku 4.5 API pricing — what it really costs

Claude Haiku 4.5 (Anthropic) costs $1 per 1M input tokens and $5 per 1M output tokens — with prompt caching, cached input drops to $0.100. Prices verified 2026-07-05; we track the price you are actually billed today, including promotional rates.

Price per 1M tokens

InputOutputCached input
$1$5$0.100

Real monthly costs on Claude Haiku 4.5

Three realistic workloads, computed from the prices above (cached share billed at the cache-read rate where the provider offers one):

Customer-support chatbot

$3.42/mo

2M input + 0.5M output tokens/month, 60% of input served from prompt cache

RAG / document Q&A

$12.40/mo

20M input + 1M output tokens/month, 70% cached (shared context)

Agentic coding assistant

$39.00/mo

50M input + 5M output tokens/month, 80% cached (long sessions)

Want exact numbers for your usage? Open the calculator — same verified prices, your token volumes.

Compare Claude Haiku 4.5

FAQ

How much does the Claude Haiku 4.5 API cost?

Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens. Cached input tokens cost $0.100 per 1M. Pricing verified 2026-07-05.

What does a typical workload cost on Claude Haiku 4.5?

Customer-support chatbot: about $3.42/month (2M input + 0.5M output tokens/month, 60% of input served from prompt cache). RAG / document Q&A: about $12.40/month (20M input + 1M output tokens/month, 70% cached (shared context)). Agentic coding assistant: about $39.00/month (50M input + 5M output tokens/month, 80% cached (long sessions))

Is Claude Haiku 4.5 expensive compared to other models?

Claude Haiku 4.5 ranks #6 of 15 models by blended price in our comparison. The cheapest tracked model is DeepSeek V4 Flash at $0.140/$0.280 per 1M tokens.