ARCHIVE PRICERETIRED MODEL200KTEXT + VISIONNO CACHE SKU
Claude 3 Haiku API Pricing
Claude 3 Haiku is retired; this archive keeps the original $0.25/$1.25 Haiku floor. $0.25/M input, $1.25/M output. It is useful for comparing the cheap Claude 3 tier against Haiku 3.5 and Haiku 4.5.
Archived input - per 1M tokens
$0.25/M
Source Anthropic retired
Archived output - per 1M tokens
$1.25/M
Use for invoice checks retired
Cached input
$0.25/M
Cache no separate SKU not listed
Effective - agentic blend
$0.33/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Archive calculator pre-loaded with Claude 3 Haiku rates. Tweak spend, output mix, or cache hit rate to compare legacy bills with current replacements.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
CODING AGENT ARCHIVE
Repo-wide bug fix
$0.029/task
LONG DOC ANALYSIS
Reading 100-page contracts
$0.054/doc
RAG SUPPORT
Support agent ticket triage
$0.002/ticket
ASSISTANT TURN
Research planning turn
$0.005/turn
§ 03 / TAPE
Price history.
Input · $0.25/M
Output · $1.3/M
Cached · $0.25/M
MAR 13 Launch at $0.25/M input and $1.25/M outputMAY 18 Retired on April 20, 2026; replacement is Claude Haiku 4.5
§ 04 / 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 —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Claude Haiku 3 | $0.25 cache $0.25 | $1.25 | $0.33 current page | 200K | Low-cost Claude archive checks |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 1M | Legacy Claude production baselines |
| Claude Haiku 4.5 | $1.00 cache $0.10 | $5.00 | $0.64 pricier | 200K | Low-cost Claude archive checks |
| Claude Opus 4.7 | $5.00 cache $0.50 | $25.00 | $3.21 pricier | 1M | Current replacement workloads |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 pricier | 1.05M | Current replacement workloads |
| Gemini 2.5 Pro | $1.25 cache $0.13 | $10.00 | $1.10 pricier | 2M | Gemini long-context work |
| DeepSeek V4 Pro | $0.43 cache $0.00 | $0.87 | $0.14 cheaper | 1M | Low-cost reasoning and coding |
Frequently asked.
Short answers for teams checking Claude 3 Haiku pricing, status, and migration choices.
Q · 01 Is Claude 3 Haiku still available? +
No. This is a retired model page kept for pricing history and invoice reconciliation.
Q · 02 How much did Claude 3 Haiku cost? +
Claude 3 Haiku is listed here at $0.25/M input and $1.25/M output.
Q · 03 Is cached-input pricing included? +
No separate cache discount was listed in the source used for this archive, so the calculator treats cached input as undiscounted.
Q · 04 What should teams use instead? +
For new work, compare against
claude-haiku-4-5 and other current rows in the shelf.Q · 05 Why keep this archive page? +
Archive pages preserve old price baselines, help explain invoice history, and capture migration search demand without implying the model is the best current choice.