AiGanakGPT-6 Luna vs Claude Haiku 5.5: API pricing
GPT-6 Luna and Claude Haiku 5.5 cost the same for a typical support answer at list prices checked 26 October 2026.
GPT-6 Luna: $0.1 input / $0.5 output per 1M tokens. Claude Haiku 5.5: $0.1 / $0.5.
Prices side by side
Sources: OpenAI, Anthropic, checked 26 October 2026. Full details: GPT-6 Luna · Claude Haiku 5.5.
| GPT-6 Luna | Claude Haiku 5.5 | |
|---|---|---|
| Input | $0.1 | $0.1 |
| Cached input | $0.01 | $0.01 |
| Output | $0.5 | $0.5 |
| Batch input / output | $0.05 / $0.25 | $0.05 / $0.25 |
| Cache write | $0.125 | $0.125 |
| Long prompts | Prompts over 272K input tokens cost 2x input and cache rates and 1.5x output for the whole request. | Requests whose prompt is over 100,000 tokens (including cache reads and writes) pay higher rates. |
| Announced change | None announced | None announced |
Cost per request
Token counts are stated so you can check the arithmetic.
| Task | Tokens | GPT-6 Luna | Claude Haiku 5.5 |
|---|---|---|---|
| Chat reply | 2,000 input tokens, none cached, 300-token reply | $0.00035 | $0.00035 |
| Support answer | 6,000 input tokens (4,000 cached instructions and help text), 500-token answer | $0.00049 | $0.00049 |
| Document summary | 20,000-token document, no caching, 800-token summary | $0.00240 | $0.00240 |
Monthly cost of support answers
| Answers per month | GPT-6 Luna | Claude Haiku 5.5 | Difference |
|---|---|---|---|
| 10,000 | $4.90 | $4.90 | $0.00000 |
| 100,000 | $49.00 | $49.00 | $0.00000 |
| 1,000,000 | $490 | $490 | $0.00000 |
Price per token is only part of the story: the model that answers in fewer tokens, or needs fewer retries, can be cheaper in practice. Test both on your own requests before switching.
GPT-6 Luna vs Claude Haiku 5.5: pricing questions
Can't find it? Press ⌘K and ask.
Is GPT-6 Luna cheaper than Claude Haiku 5.5?
GPT-6 Luna and Claude Haiku 5.5 cost the same for a typical support answer at list prices checked 26 October 2026.
How much more does GPT-6 Luna cost than Claude Haiku 5.5?
For a support answer with 6,000 input tokens (4,000 cached) and a 500-token reply, GPT-6 Luna costs the same than Claude Haiku 5.5: $0.490 against $0.490 per 1,000 answers.
What do GPT-6 Luna and Claude Haiku 5.5 cost with batch processing?
Batch prices per million tokens: GPT-6 Luna $0.05 input / $0.25 output, Claude Haiku 5.5 $0.05 / $0.25. Batch requests return within 24 hours.
Should I switch from GPT-6 Luna to Claude Haiku 5.5?
Only if quality holds on your own examples. Price per token is one factor; how many tokens each model uses for your task, and how often its answers need a retry, decide the real cost. Test both on 50 to 100 real requests before switching.
Related price comparisons
Claude Haiku 5.5 vs Gemini 3.5 Flash-Lite · GPT-6 Luna vs Gemini 3.5 Flash-Lite · all comparisons
Get an email when GPT-6 Luna, Claude Haiku 5.5 or any other LLM price changes
OpenAI, Anthropic and Google change API prices with little notice. We check their pricing pages every week and email you the old price, the new price and the date. Free, a few emails a month at most.
Want to know what your own LLM bill could save?
Upload a usage export to the free Bill Analyzer, or order the LLM Cost Report for a ranked savings plan.