$0LLM Cost IntelligenceClient-Side FinOps & Token Budgeting
Anthropic First-PartyVerified 2026-11-12

Claude Haiku 5.5 API Pricing & Cost Rules

API Model ID: claude-haiku-5-5 · Context Window: 1,000,000 tokens · Max Output: 128,000 tokens

Context Tiers & Token Rate Card (USD per 1M Tokens)

TierStd InputStd OutputCache ReadWrite (Short)Write (Long)
Standard (<= 100K)$0.1$0.5$0.01$0.125$0.2
Long Context (> 100K)$0.5$2.5$0.05$0.625$1.00

Prompt Caching Rules

Supported: Yes (explicit)

Minimum Cacheable Prefix: 512 tokens

Hourly Cache Storage: $0

Read = 0.10x (90% off). Write = 1.25x (5m) or 2.0x (1h). Min 512 tokens. Total input (input + cache_read + cache_write) >100K triggers 5x tier.

Batch API & Hosting Notes

Batch Supported: Yes (50% discount · Up to 24h)

Caching in Batch: Allowed + Batch discount stacks onto cache reads

50% off; stacks with caching and <=100K/>100K tier. Supports up to 300K output tokens in Batch with beta header.

US-only data residency adds 1.1x multiplier.