Claude Haiku 4.5 vs GPT-5.6 Luna: API Pricing Comparison

Anthropic Claude Haiku 4.5 vs OpenAI GPT-5.6 Luna: token prices, batch and cache rates, Arena ELO, and cost per request for 8 business use cases. Prices in USD per 1 million tokens. Data snapshot: 2026-09-06.

Claude Haiku 4.5 pricing (Anthropic)

GPT-5.6 Luna pricing (OpenAI)

Cost per request by business use case

List price vs optimized (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates).

Use caseTokens (in/out)Claude Haiku 4.5 listClaude Haiku 4.5 optimizedGPT-5.6 Luna listGPT-5.6 Luna optimized
Support Ticket1,500 / 500$0.0040$0.0032$0.000900$0.000738
Knowledge Q&A2,000 / 800$0.0060$0.0047$0.0014$0.0011
Meeting Summary10,000 / 1,200$0.016$0.0076$0.0034$0.0016
Marketing Content2,500 / 1,800$0.011$0.011$0.0027$0.0026
Coding Task3,000 / 2,000$0.013$0.012$0.0030$0.0027
Invoice Processing1,500 / 600$0.0045$0.0021$0.0010$0.000474
Call Summary2,000 / 700$0.0055$0.0027$0.0012$0.000604
Agent Workflow6,000 / 3,000$0.021$0.017$0.0048$0.0040

Open this comparison in the interactive compare tool: add up to two more models, copy a shareable link, or export the table as CSV.

These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.