ARCHIVE PRICERETIRED MODEL200KTEXT MODELPROMPT CACHING
Claude Haiku 3.5 API Pricing
Claude Haiku 3.5 is retired on the first-party Claude API. $0.8/M input, $4/M output, and $0.08/M cache-hit input. Anthropic's current pricing table keeps the final Haiku 3.5 row for archive and partner-platform context.
Archived input - per 1M tokens
$0.80/M
Source Anthropic retired
Archived output - per 1M tokens
$4.00/M
Use for invoice checks retired
Cached input - 90% off
$0.08/M
Cache reads -90%
Effective - agentic blend
$0.51/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Archive calculator pre-loaded with Claude Haiku 3.5 rates. Tweak spend, output mix, or cache hit rate to compare historical 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 RETIRED
Repo-wide bug fix
$0.045/task
LONG DOC ANALYSIS RETIRED
Reading 100-page contracts
$0.069/doc
RAG SUPPORT RETIRED
Support agent ticket triage
$0.005/ticket
ASSISTANT TURN RETIRED
Research planning turn
$0.011/turn
§ 03 / TAPE
Price history.
Input · $0.80/M
Output · $4/M
Cached · $0.08/M
NOV 04 Launch-era price at $0.80/M input and $4/M outputMAY 18 Retired on Claude API; 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 3.5 | $0.80 cache $0.08 | $4.00 | $0.51 current archive | 200K | Low-latency Claude workloads |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 1M | Production Claude agents |
| Claude Sonnet 4.5 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 200K | Production Claude agents |
| Claude Haiku 4.5 | $1.00 cache $0.10 | $5.00 | $0.64 pricier | 200K | Low-latency Claude workloads |
| Claude Opus 4.7 | $5.00 cache $0.50 | $25.00 | $3.21 pricier | 1M | Frontier reasoning and hard code |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 pricier | 1.05M | OpenAI production apps |
| 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 old Claude Haiku 3.5 costs or migrating archive workloads.
Q · 01 Is Claude Haiku 3.5 still available? +
Claude Haiku 3.5 is retired on the first-party Claude API. Keep this page for archive pricing, old invoices, and migration planning.
Q · 02 What replaced Claude Haiku 3.5? +
Anthropic lists
claude-haiku-4-5 as the recommended replacement in its model deprecations page.Q · 03 How much did Claude Haiku 3.5 cost? +
Claude Haiku 3.5 is archived at $0.8/M input and $4/M output.
Q · 04 Does this archive include prompt caching? +
Cache-hit input is archived at $0.08/M, matching Anthropic's 10% cache-read multiplier on this price tier.
Q · 05 Can I use this for new production routing? +
Use the archive for cost history, not fresh routing decisions. Compare the current Claude rows in the shelf before starting new workloads.
Q · 06 Why keep a page for a retired model? +
Retired-model pages help teams reconcile historical spend, understand migration economics, and answer old search demand without pretending the model is current.