Last checked 27 Oct 2026
Claude Haiku 5.5 vs GPT-6 Luna
Claude Haiku 5.5 is billed by Anthropic. GPT-6 Luna is billed by OpenAI. A pair is two models from different providers whose higher published input rate is at most 1.5 times the lower one, and whose higher published output rate is at most 1.5 times the lower one. Closer rates are listed first. Each model is in at most 2 pairs, and the list stops at 12. The figures below are the rates stored on those two rows, the differences between them, and the cost of one sample workload. This page does not score quality.
Stored rates
Claude Haiku 5.5 (Anthropic, Prompts up to 100K tokens) and GPT-6 Luna (OpenAI, Standard, under 272K). Provider pages: Anthropic and OpenAI.
| Field | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Input / 1M | $0.10 | $0.10 |
| Cached input / 1M | $0.01 | $0.01 |
| Output / 1M | $0.50 | $0.50 |
| Rate | Prompts up to 100K tokens | Standard, under 272K |
| Context | 1M | 1.05M |
| Max output | 128k | 128k |
| Status | Active | Active |
| Modalities | n/a | text, image → text |
| Released | 7 Oct 2026 | 22 Sep 2026 |
| Checked | 27 Oct 2026 | 27 Oct 2026 |
| Per request | $0.0006 | $0.0006 |
| Per month | $18.00 | $18.00 |
Sample workload
The sample is the calculator's starting workload: 2,000 input tokens and 800 output tokens per request, 1,000 requests a day. A month in the calculator is 30 days, so that is 30,000 requests. The cost uses the stored input and output rates only. Cache hits, batch discounts, long-context surcharges, peak hours, and prices scheduled after an introductory window are not included. The rate label and the notes below name those other published rates.
Claude Haiku 5.5 is $0.0006 per request and $18.00 per month ($6.00 input and $12.00 output over the month). GPT-6 Luna is $0.0006 per request and $18.00 per month ($6.00 input and $12.00 output over the month).
On this sample the two stored rates cost the same amount.
Open Claude Haiku 5.5 in the calculatorOpen GPT-6 Luna in the calculator
Notes from the sources
Claude Haiku 5.5
Prompts up to 100K tokens
Rate for prompts up to 100,000 tokens. The same pricing table lists prompts over 100,000 tokens at $0.50 input, $0.05 cache hits, and $2.50 output per 1M tokens. Cache writes are $0.125 (5-minute) and $0.20 (1-hour) at the short rate. Context is published as 1M tokens and max output as 128K. Modalities were not listed on the pages checked.
GPT-6 Luna
Standard, under 272K
Short-context standard rate for prompts under 272K tokens. The same pricing table lists long-context rates of $0.20 input, $0.02 cached input, and $0.75 output per 1M tokens. Batch and Flex are half of standard. Context window 1.05M and max output 128K are from the OpenAI API model list.