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

Claude Sonnet 5.5 API Pricing & Cost Rules

API Model ID: claude-sonnet-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 (<= 1M)$2.00$10.00$0.1$2.5$4.00

Prompt Caching Rules

Supported: Yes (explicit)

Minimum Cacheable Prefix: 512 tokens

Hourly Cache Storage: $0

Read = 0.05x (95% off = $0.10/1M). Write = 1.25x (5m) or 2.0x (1h). Min 512 tokens. Claude 4.7+ tokenizer produces ~30% more tokens.

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 ($0.05/1M read, $1.25 5m, $2.00 1h). Supports up to 300K output tokens in Batch with beta header.

US-only data residency (inference_geo: 'us') adds 1.1x multiplier.