AnthropicStableChecked 2026-07-12

Claude Haiku 4.5 pricing, context window, and cost calculator

An Anthropic model with tracked standard, cached-input, and cache-write pricing.

Verified fields

Quick facts

ProviderAnthropic
API model IDclaude-haiku-4-5-20251001
Default input / 1M$1.00
Default output / 1M$5.00
Context window200,000
Default profilestandard
Acceptstext, image
Producestext
Knowledge cutoff2025-02
StatusStable
Maximum output64,000 tokens

Supported capabilities

  • Streaming
  • Function calling
  • Structured outputs
  • Prompt caching
  • Batch API
  • Reasoning

Only capabilities explicitly tracked from provider documentation are shown.

Source-tracked rates

Verified pricing profiles

Amounts are USD per 1M tokens unless the column states an hourly storage unit.

ProfileInput / 1MCached input / 1MCache write / 1MOutput / 1MNotes
standardDefault$1.00 USD$0.10 USD$1.25 USD (5m) / $2.00 USD (1h)$5.00 USDUsed for default estimates.
Workload estimate

Claude Haiku 4.5 cost calculator

Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.

Estimated monthly total$35.00
Monthly input cost
$10.00
Monthly output cost
$25.00
Per 1,000 requests
$3.50
Active profile
standard

Estimate excludes untracked provider-specific charges.

Explicit assumptions

Common workload examples

Input only

1M input tokens

$1.00 under the standard profile, excluding output and other charges.

Output only

1M output tokens

$5.00 under the standard profile, excluding input and other charges.

Default workload

10,000 monthly requests

At 1,000 input and 500 output tokens per request: $35.00 under standard.

Cache scenario

50% cached input

The same default workload with 50% cached input is estimated at $30.50. Cache savings apply only to the tracked cached-input rate.

Verification

Sources and methodology

Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.

Calculator profile rule: standard is the verified default. Regional and platform-specific pricing may differ.