GPT OSS 120B vs GPT-6 Luna
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 OSS 120Bopenai/gpt-oss-120b | GPT-6 Lunaopenai/gpt-6-luna |
|---|---|---|
| Maker | openai | openai |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.105 | $0.105 |
| Cached input per 1M tokens | Not applicable | $0.0105 |
| Cache write per 1M tokens | Not applicable | $0.13125 |
| Output per 1M tokens | $0.525 | $0.525 |
| Context window | 131,072 tokens | 1,050,000 tokens Larger |
| Max output | 131,072 tokens Larger | 128,000 tokens |
| Capabilities | Reasoning, tool use | Reasoning, tool use, vision, file input, web search, fast |
| Takes | Text | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2025-08-05 | 2026-09-22 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | GPT OSS 120B | GPT-6 Luna |
|---|---|---|
| 1,000 tokens in, 200 out | $0.00021 | $0.00021 |
| 10,000 tokens in, 1,000 out | $0.001575 | $0.001575 |
| 100,000 tokens in, 4,000 out | $0.0126 | $0.0126 |