Anthropic Claude
Claude Haiku 5.5
$0.20 / 1M tokens
cheapest at Anthropic · $0.10 in · $0.50 out
Wins 2 of 4
Head to head · prices updated Oct 31, 2026
Claude Haiku 5.5 and GPT-6 Luna cost about the same at their cheapest providers.
Anthropic Claude
$0.20 / 1M tokens
cheapest at Anthropic · $0.10 in · $0.50 out
Wins 2 of 4
OpenAI
$0.20 / 1M tokens
cheapest at OpenAI · $0.10 in · $0.50 out
Wins 1 of 4
Verdict
Claude Haiku 5.5 and GPT-6 Luna cost about the same at their cheapest providers.
GPT-6 Luna scores higher on GPQA Diamond: 90.5% (max reasoning) vs 89.6% (max reasoning).
Claude Haiku 5.5 accepts longer prompts (1000K vs 922K tokens).
Your monthly bill
Both cost the same for this workload.
| Claude Haiku 5.5 | GPT-6 Luna | |
|---|---|---|
| Cheapest blended price / 1M | $0.20 | $0.20 |
| Input / output per 1M | $0.10 / $0.50 | $0.10 / $0.50 |
| Accuracy (GPQA Diamond) | 89.6% (max reasoning) | 90.5% (max reasoning) |
| Max context | 1M | 922K |
| Providers we track | 4 | 3 |
Standard list prices at each model's cheapest provider we track; blended = 3 input : 1 output tokens. GPQA Diamond from Epoch AI (CC BY 4.0), best measured reasoning setting, named next to each score. Methodology.
Claude Haiku 5.5 and GPT-6 Luna cost about the same at their cheapest providers.
On GPQA Diamond (graduate-level science questions, measured by Epoch AI) Claude Haiku 5.5 scores 89.6% (max reasoning) and GPT-6 Luna 90.5% (max reasoning). One benchmark is not the whole picture; test both on your own prompts.
From $0.10 input and $0.50 output per 1M tokens at Anthropic, the cheapest of 4 providers we track.
From $0.10 input and $0.50 output per 1M tokens at OpenAI, the cheapest of 3 providers we track.
Swap a model