Model comparison
Claude Haiku 4.5 vs GPT-5.6 Luna
A spec-by-spec comparison of Claude Haiku 4.5 and GPT-5.6 Luna: pricing, context window, capabilities, and independently sourced benchmarks.
Head-to-head
- GPT-5.6 Luna costs 5.0x less per input token than Claude Haiku 4.5 ($0.20/MTok vs $1.00/MTok).
- GPT-5.6 Luna has a 5.3x larger context window than Claude Haiku 4.5 (1,050,000 tokens vs 200,000 tokens).
| Spec | Claude Haiku 4.5 | GPT-5.6 Luna |
|---|---|---|
| Provider | anthropic | openai |
| Family | Claude Haiku | GPT-5.6 |
| Status | current | current |
| Release date | 2025-10-15 | — |
| Knowledge cutoff | 2025-02 | 2026-02-16 |
| Context window | 200,000 tokens | 1,050,000 tokens |
| Max output tokens | 64,000 tokens | 128,000 tokens |
| Input price | $1.00/MTok | $0.20/MTok |
| Output price | $5.00/MTok | $1.20/MTok |
| Cached input price | $0.10/MTok | $0.02/MTok |
| Vision | Yes | Yes |
| Tool use | Yes | Yes |
| Extended thinking | Yes | Yes |
| Streaming | — | — |
Claude Haiku 4.5
Strengths- The only current Claude model that supports classic extended thinking.
- Uses the older Claude tokenizer, so token counts are ~30% lower than Sonnet 5 for the same text.
- Reliable knowledge cutoff of Feb 2025 is the oldest in the current Claude lineup.
- 200k context window against 1M on every other current Claude model.
- Does not support adaptive thinking.
GPT-5.6 Luna
Strengths- Retains the full 1.05M context window and 128K max output of the GPT-5.6 family.
- Priced at $0.20/$1.20/$0.02 per MTok as of 2026-09-24, an 80% cut from the 2026-07-17 pass’s $1.00/$6.00/$0.10.
- Input price doubles to $0.40/MTok and output rises to $1.80/MTok on the long-context tier.
Not sure which one to use?
Flaibo is a daily AI orientation hub: a 12-week path and a prompt vault, with Free and Professional plans. Build the habit, not just the comparison.
Start your AI path