Claude Haiku 4.5 API Pricing: Cost Calculator & Real Examples (2026)
Claude Haiku 4.5 charges $1.00 per 1 million input tokens and $5.00 per 1 million output tokens. But per-token prices don't answer the real question: what will your workload cost per month? Below we compute it for three realistic scenarios — or run your own numbers with Claude Haiku 4.5 preselected.
| Meter | Price per 1M tokens |
|---|---|
| Input | $1.00 |
| Cached input | $0.10 |
| Output | $5.00 |
What does Claude Haiku 4.5 cost in practice?
| Monthly scenario | Token bill |
|---|---|
| Support chatbot (150k requests, 400 in / 300 out tokens) | $285.00 |
| Document workflow (22k runs, 3,000 in / 400 out tokens) | $110.00 |
| High-volume classifier (1M requests, 300 in / 10 out tokens) | $350.00 |
In the chatbot scenario, output is ~79% of the Claude Haiku 4.5 bill — capping response length (max tokens) is the most direct optimization. Document workflows are input-heavy, so the input rate dominates there.
Prompt caching savings
Claude Haiku 4.5 offers cached input at $0.10/1M (vs $1.00 standard). At a 60% cache-hit rate, the example chatbot drops from $285.00 to $252.60/month — saving $32.40. If your system prompt and context are stable, this discount is free money.
Is Claude Haiku 4.5 cheap or expensive?
On the same chatbot workload, Claude Haiku 4.5 is cheaper than 9 of the 13 models we track (position 5 of 14, cheapest to priciest). The nearest cheaper alternative is GPT-5.4 mini ($247.50/month on the same scenario). One step up: GPT-5.6 Luna ($330.00/month). The right decision isn't absolute price but the cheapest model that meets your quality bar — test before overpaying.
FAQ
How much does Claude Haiku 4.5 cost per 1M tokens?
$1.00 per 1M input tokens and $5.00 per 1M output tokens (verified 2026-07-09).
What does a chatbot cost on Claude Haiku 4.5?
A 500-active-user chatbot (10 questions/day, 400 input + 300 output tokens per request) costs ~$285.00/month in tokens on Claude Haiku 4.5. Adjust the assumptions in the calculator.
Our take on this model
Haiku 4.5 is Anthropic's fast tier and the quiet favorite for support chatbots: strong instruction-following at mini prices means fewer malformed answers to review — and review minutes are a real cost line most chatbot budgets forget.
It competes directly with GPT mini-class and Gemini Flash. Haiku tends to win where tone and safety of customer-facing text matter; the others where raw throughput price does.
Prices verified on 2026-07-09 against the provider's official pricing page. Estimates are for planning purposes only — always confirm current pricing with the provider.