FAST BUDGET CLAUDE200K CONTEXTTEXTPROMPT CACHINGBATCH -50%
Claude Haiku 4.5 API Pricing
Anthropic's lowest-cost Claude 4.5 model for classification, support automation, routing, and high-volume text work — $1/M input, $5/M output, with cache reads at $0.10/M. Use it when Sonnet quality is unnecessary and throughput matters more than deep reasoning. Pulled directly from platform.claude.com daily.
Input · per 1M tokens
$1.00/M
Stable 45 days ↔ flat
Output · per 1M tokens
$5.00/M
Stable 45 days ↔ flat
Cached input · 90% off
$0.10/M
Cache 5min or 1h −90%
Effective · agentic blend
$0.64/M
92/8 split · 82% cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current Claude Haiku 4.5 rates. Tweak amount, workload split, or cache hit rate — share the URL to share the calculation.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
CLASSIFICATION
Lead scoring classifier
$0.002/record
CUSTOMER SUPPORT
Support bot first reply
$0.003/ticket
BULK RAG
Knowledge base answering
$0.007/answer
LIGHT AGENT
Back-office data cleanup
$0.015/task
§ 03 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · anthropic-bpe-estimate · ≈3.5 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters 401
Words 62
Tokens (estimated) 115 tokens
Cost as input · uncached $0.000115 USD
Cost as output · uncached $0.000575 USD
Cost as cached input $0.000012 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Claude Haiku 4.5 Current | $1.00 cache $0.10 | $5.00 | $0.64 agentic 92/8 | 200K | Classification · support automation |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 1M | Production agents · coding |
| Claude Sonnet 4.5 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 200K | Stable Sonnet migrations |
| Claude Opus 4.5 | $5.00 cache $0.50 | $25.00 | $3.21 pricier | 200K | Frontier coding · long-form writing |
| GPT-5.4 nano | $0.20 cache $0.02 | $1.25 | $0.15 cheaper | short | Low-cost routing · simple extraction |
| Gemini 3.1 Flash-Lite | $0.25 cache $0.03 | $1.50 | $0.18 cheaper | 1M | High-volume agents · translation |
| DeepSeek V4 Flash | $0.14 cache $0.00 | $0.28 | $0.05 cheaper | 1M | Ultra-cheap bulk generation |
| DeepSeek V4 Pro | $0.43 cache $0.00 | $0.87 | $0.14 discounted | 1M | Budget reasoning · tool use |
Frequently asked.
Practical pricing questions for using Haiku as the cheap Claude workhorse.
Q · 01 Is Claude Haiku 4.5 the cheapest Claude model? +
Yes. Anthropic lists Claude Haiku 4.5 at
$1/M input and $5/M output, below Sonnet 4.6 at $3/M and $15/M. With an 82% cache hit rate and a 92/8 input-output workload, Haiku's effective blended cost is $0.64/M.Q · 02 How does prompt caching work for Haiku 4.5? +
Cache hits are billed at
$0.10/M, which is 10% of the $1/M base input price. Cache writes cost $1.25/M for a 5-minute cache and $2/M for a 1-hour cache. Use caching for stable system prompts, policy text, retrieved context, and repeated instructions.Q · 03 When was the last price change? +
We did not find a public price change after launch. AI//COST tracks Claude Haiku 4.5 from April 02, 2026, and the live Anthropic pricing table still shows
$1/M input, $0.10/M cache hits, and $5/M output as of May 17, 2026.Q · 04 Is there a Batch API discount? +
Yes. Anthropic's Batch API applies a 50% discount to both input and output tokens. For Claude Haiku 4.5, the batch table lists
$0.50/M input and $2.50/M output, compared with the standard $1/M and $5/M rates.Q · 05 Does Haiku 4.5 have regional pricing differences? +
The first-party Claude API uses global routing at standard list price by default. Anthropic says regional and multi-region partner endpoints on Bedrock and Vertex AI include a 10% premium for Claude 4.5 models and later. The first-party
inference_geo 1.1x data-residency multiplier applies to Claude Opus 4.6, Claude Sonnet 4.6, and later models, not Haiku 4.5.Q · 06 Does Haiku 4.5 support vision? +
The Anthropic provider lineup in this repo treats Claude Haiku 4.5 as text-only. Use it for text classification, extraction, support drafts, and routing. For image input or higher reasoning quality, move up to Sonnet 4.6 or Opus 4.5 and price the workload separately.
Q · 07 Are volume discounts published? +
No public volume-discount ladder is published for Haiku. Anthropic says volume discounts may be available for high-volume users and are negotiated case by case. Standard API users should assume the public
$1/M and $5/M rates unless they have a separate enterprise agreement.Q · 08 How accurate is the tokenizer estimate? +
The live counter uses a
4.875 English characters-per-token estimate for Claude-class BPE tokenization. It is useful for planning, but final billing uses Anthropic's server-side token count. Code, tables, and non-Latin scripts can differ materially from the English estimate.