GPT-5 nano vs GPT-6 Luna (Batch)
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | GPT-5 nanoopenai/gpt-5-nano | GPT-6 Luna (Batch)openai/gpt-6-luna-batch |
|---|---|---|
| Maker | openai | openai |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.0525 | $0.0525 |
| Cached input per 1M tokens | $0.00525 | $0.00525 |
| Cache write per 1M tokens | Same as input | $0.065625 |
| Output per 1M tokens | $0.42 | $0.2625 Lower |
| Context window | 400,000 tokens | 1,050,000 tokens Larger |
| Max output | 128,000 tokens | 128,000 tokens |
| Capabilities | Reasoning, tool use, vision, file input, web search | Reasoning, tool use, vision, file input |
| Takes | Text, image, pdf | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2025-08-07 | 2026-09-22 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | GPT-5 nano | GPT-6 Luna (Batch) |
|---|---|---|
| 1,000 tokens in, 200 out | $0.000137 | $0.000105 |
| 10,000 tokens in, 1,000 out | $0.000945 | $0.000788 |
| 100,000 tokens in, 4,000 out | $0.00693 | $0.0063 |