Claude Haiku 4.5 API Pricing: $1.00 / $5.00 per 1M Tokens
The numbers: Claude Haiku 4.5 (Anthropic) bills $1.00 per 1M input tokens, $5.00 per 1M output tokens, and $0.10 per 1M cached input tokens, inside a 200K context window. On our reference 200-step agent workload that works out to about $1.35 per task.
Fast current Claude model for high-volume and latency-sensitive work. Every figure on this page was read directly from Anthropic’s own documentation on September 18, 2026 — not copied from a third-party comparison table. Rates change; the source link and check date below are part of the data.
Verified rates
| Item | Rate | Unit |
|---|---|---|
| Input | $1.00 | per 1M tokens |
| Output | $5.00 | per 1M tokens |
| Cached input (cache read) | $0.10 | per 1M tokens |
| Context window | 200K | tokens |
Source: Anthropic official pricing ↗, checked September 18, 2026.
What a real workload costs on Claude Haiku 4.5
List rates are not bills. These two reference workloads translate the table above into money. The assumptions are visible so you can swap in your own trace — the cost calculator does exactly that.
Scenario A — one 200-step agent task
A coding agent runs 200 steps against a stable 40,000-token prefix (system prompt, tools, repository map). The prefix is written to cache on the first step, re-read on the remaining 199, and each step produces 500 output tokens. For Anthropic, cache writes bill at 1.25x the input rate.
| Component | Calculation | Cost |
|---|---|---|
| Cache write (once) | 40,000 tokens × $1.25 / 1M | $0.05 |
| Cache reads | 199 × 40,000 × $0.10 / 1M | $0.80 |
| Output | 200 × 500 × $5.00 / 1M | $0.50 |
| Total per task | $1.35 |
Scenario B — one heavy month
A production service pushes 50M fresh input tokens, 150M cached input tokens, and 10M output tokens through Claude Haiku 4.5 in a month:
| Component | Volume | Cost |
|---|---|---|
| Fresh input | 50M × $1.00 | $50.00 |
| Cached input | 150M × $0.10 | $15.00 |
| Output | 10M × $5.00 | $50.00 |
| Monthly total | $115.00 |
Head-to-head cost comparisons
- Claude Haiku 4.5 vs Gemini 3.8 Flash — same workload, $1.35 vs $0.97 (1.4x apart).
Frequently asked questions
How much does Claude Haiku 4.5 cost per million tokens?
Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, with cached input at $0.10 per 1M. Verified September 18, 2026 against Anthropic's official pricing.
What is the context window of Claude Haiku 4.5?
Claude Haiku 4.5 supports a 200K token context window, per Anthropic's documentation checked September 18, 2026.
Does Claude Haiku 4.5 support prompt caching?
Yes. Cached input tokens bill at $0.10 per 1M instead of the full input rate; cache writes bill at 1.25x the input rate.
When was this Claude Haiku 4.5 price last checked?
On September 18, 2026, against Anthropic's own pricing page: https://platform.claude.com/docs/en/about-claude/pricing