Claude Haiku 5.5 vs GPT-6 Luna
Identical headline pricing — $0.1 / $0.5 per 1M on both. The difference is generation, not price.
Side by Side
| Claude Haiku 5.5 | GPT-6 Luna | |
|---|---|---|
| Input /1M | $0.1 | $0.1 |
| Output /1M | $0.5 | $0.5 |
| Cache /1M | $0.125 | $0.01 |
| Batch in/out | $0.05/$0.25 | $0.05/$0.25 |
| Context | — | — |
| Tiers | long ctx >100K: $0.50 in / $2.50 out | long ctx: $0.20 in / $0.75 out |
Workload Cost Calculator
Claude Haiku 5.5:
GPT-6 Luna:
Difference:
Frequently Asked Questions
Haiku 5.5 vs GPT-6 Luna — same price?
Yes, both at $0.10/$0.50 per 1M for base tier. Haiku 5.5 adds a long-context tier at $2.50/$1.00.
Which is better for high-volume tasks?
Both are ultra-budget. Haiku 5.5 has Claude's safety features; Luna has GPT-6 architecture.