GPT-6 Luna vs Gemini 3.8 Flash
A side-by-side comparison of GPT-6 Luna from OpenAI and Gemini 3.8 Flash from Google, using published pricing, context windows, supported inputs, and release dates.
- GPT-6 Luna input
- $0.1
- Gemini 3.8 Flash input
- $0.825
Key differences
GPT-6 Luna is 88% cheaper on input tokens ($0.1 vs $0.825 per 1M).
GPT-6 Luna has the larger context window: 1.05M vs 1.05M tokens.
GPT-6 Luna is the newer release (Sep 22, 2026, vs Sep 2, 2026).
GPT-6 Luna vs Gemini 3.8 Flash specs
| Spec | GPT-6 Luna | Gemini 3.8 Flash |
|---|---|---|
| Provider | OpenAI | |
| Released | Sep 22, 2026 | Sep 2, 2026 |
| Context window | 1,050,000 tokens | 1,048,576 tokens |
| Input price / 1M tokens | $0.1 | $0.825 |
| Output price / 1M tokens | $0.5 | $4.13 |
| 10K in + 1K out request | $0.0015 | $0.012 |
| Accepts | file, image, text | audio, file, image, text, video |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning | Yes | Yes |
| Popularity | 48/100 | 39/100 |
Highlighted values are better on that spec: lower price, larger context window, newer release, or higher popularity. Prices in USD per 1M tokens as listed on OpenRouter.
GPT-6 Luna vs Gemini 3.8 Flash questions
Is GPT-6 Luna or Gemini 3.8 Flash cheaper?
GPT-6 Luna has the lower listed input price ($0.1 per million tokens). For a request with 10,000 input and 1,000 output tokens, GPT-6 Luna costs about $0.0015 and Gemini 3.8 Flash about $0.012.
Which has the larger context window?
GPT-6 Luna supports 1,050,000 tokens, the larger of the two.
Which model should I choose?
Pick the cheaper model for high-volume, simpler tasks, and test both on a sample of your real prompts before committing. Price and context size do not measure output quality on your specific workload.