High-volume, cost-sensitive work
Either one
Both cost $0.20 per million tokens on a typical mix of three input tokens for every output token.
Claude Haiku 5.5 vs GPT-6 Luna: price, context and capabilities
Choose Claude Haiku 5.5 for the hardest reasoning tasks, the latest release and the most recent knowledge; on the other points the two are level or the data is missing.
In short
- Both cost the same at the headline price ($0.20 / 1M tokens).
- GPT-6 Luna reads more per request: 1.05M tokens against 1M.
- Claude Haiku 5.5 is the newer model (October 2026, against Sep 22, 2026).
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Hardest reasoning tasks
Choose Claude Haiku 5.5
Claude Haiku 5.5 scores 43.4 on the Artificial Analysis Intelligence Index, against 38.1 for GPT-6 Luna.
Reasoning over long documents
Either one
They are practically level on Long-context reasoning (AA-LCR) (82.7% and 83.3%).
Latest release
Choose Claude Haiku 5.5
Claude Haiku 5.5 is the newer release (October 2026, against Sep 22, 2026 for GPT-6 Luna).
Most recent knowledge
Choose Claude Haiku 5.5
Claude Haiku 5.5 was trained on data up to June 2026, against May 2026 for GPT-6 Luna.
Monthly cost at three volumes
| Volume | Claude Haiku 5.5 | GPT-6 Luna | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.23 | $0.23 | = |
| Production: 20M input, 5M output tokens | $4.50 | $4.50 | = |
| Scale: 500M input, 100M output tokens | $100.00 | $100.00 | = |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| Claude Haiku 5.5 | GPT-6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Category | Language models | Language models |
| Status | Generally available | Generally available |
| Headline price | $0.20 / 1M tokens | $0.20 / 1M tokens |
| Input | $0.10 / 1M tokens | $0.10 / 1M tokens |
| Output | $0.50 / 1M tokens | $0.50 / 1M tokens |
| Cached input | $0.01 / 1M tokens | $0.01 / 1M tokens |
| Context window | 1M | 1.05M |
| Max output | 128k | 128k |
| Released | October 2026 | Sep 22, 2026 |
| Knowledge cutoff | June 2026 | May 2026 |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | claude-haiku-5-5 | gpt-6-luna |
Benchmarks side by side
Leader in bold.
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Intelligence Index | 43.4 | 38.1 |
| SciCode | 55% | 54.6% |
| Humanity's Last Exam | 44.4% | 38.5% |
| Long-context reasoning (AA-LCR) | 82.7% | 83.3% |
| MMMU-Pro (visual reasoning) | No data | 79.7% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose Claude Haiku 5.5 or GPT-6 Luna?
Choose Claude Haiku 5.5 for the hardest reasoning tasks, the latest release and the most recent knowledge; on the other points the two are level or the data is missing.
Which is cheaper, Claude Haiku 5.5 or GPT-6 Luna?
Both cost the same at the headline price ($0.20 / 1M tokens).
Which has the larger context window, Claude Haiku 5.5 or GPT-6 Luna?
GPT-6 Luna reads more per request: 1.05M tokens against 1M.
What is the difference between Claude Haiku 5.5 and GPT-6 Luna?
Claude Haiku 5.5 is made by Anthropic and GPT-6 Luna by OpenAI. Both cost the same at the headline price ($0.20 / 1M tokens). GPT-6 Luna reads more per request: 1.05M tokens against 1M. Claude Haiku 5.5 is the newer model (October 2026, against Sep 22, 2026).
How much do Claude Haiku 5.5 and GPT-6 Luna cost per month?
At 20 million input and 5 million output tokens a month, Claude Haiku 5.5 costs $4.50 and GPT-6 Luna costs $4.50, at standard rates.
Which is newer, Claude Haiku 5.5 or GPT-6 Luna?
Claude Haiku 5.5 was released on October 2026 and GPT-6 Luna on Sep 22, 2026.