Prices → Compare → GPT-5.6 Luna vs Claude Haiku 4.5
GPT-5.6 Luna vs Claude Haiku 4.5: API cost compared
GPT-5.6 Luna lists at $0.100 in / $0.600 out per 1M tokens. Claude Haiku 4.5 lists at $1.000 in / $5.000. Sticker price only tells you so much — below is what each actually costs across eight production workloads.
Side by side
| GPT-5.6 Luna | Claude Haiku 4.5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Input per 1M | $0.100 | $1.000 |
| Output per 1M | $0.600 | $5.000 |
| Cached input per 1M | $0.010 | $0.100 |
| Context window | 400k | 200k |
| Blended per 1M (3:1) | $0.225 | $2.000 |
Monthly cost by workload
Caching applied at each workload's typical hit rate. This is where the two models actually separate.
| Workload | GPT-5.6 Luna | Claude Haiku 4.5 | Cheaper | Difference |
|---|---|---|---|---|
| Customer support chatbot | $14.64 | $128.90 | GPT-5.6 Luna | $114.26 (89%) |
| RAG document Q&A | $19.60 | $184.00 | GPT-5.6 Luna | $164.40 (89%) |
| Coding agent | $10.45 | $92.50 | GPT-5.6 Luna | $82.05 (89%) |
| Bulk summarization | $138.60 | $1,346 | GPT-5.6 Luna | $1,207 (90%) |
| Structured data extraction | $187.00 | $1,745 | GPT-5.6 Luna | $1,558 (89%) |
| Long-form content generation | $25.46 | $214.60 | GPT-5.6 Luna | $189.14 (88%) |
| Email triage agent | $43.25 | $402.50 | GPT-5.6 Luna | $359.25 (89%) |
| Translation pipeline | $164.47 | $1,405 | GPT-5.6 Luna | $1,240 (88%) |
How to read this
GPT-5.6 Luna is cheaper on the majority of these workloads, but "majority" is not the decision. The output:input price ratio is 6.0 for GPT-5.6 Luna and 5.0 for Claude Haiku 4.5. If your traffic is output-heavy — long-form drafting, translation — the model with the lower output price wins regardless of what the input price suggests. If you are input-heavy — RAG, bulk summarization, agents re-reading a codebase — the cached input rate matters more than either headline number.
Cost is also not the only axis. This site does not benchmark quality, latency, or rate limits, and a model that is 3x cheaper but needs two attempts per task is not cheaper. Use these numbers to size a bill, then validate on your own evals.
Run your own numbers
Cost calculator
Enter your own numbers, or start from a workload preset. Costs are monthly and update as you type.
| Model | In /1M | Out /1M | Monthly | vs best |
|---|