Gemini 3.5 Flash vs GPT-6 Luna: price, context window and capabilities
Gemini 3.5 Flash (google/gemini-3.5-flash) from Google and GPT-6 Luna (openai/gpt-6-luna) from OpenAI are both multimodal language models on the OceanToken API. GPT-6 Luna costs less per token than Gemini 3.5 Flash: $0.09 against $1.35 per 1M input tokens (93% less) and $0.45 against $8.10 per 1M output tokens (94% less). Both are 10% off their official price on OceanToken, for every account. Their context windows are almost the same size, about 1.05M tokens: GPT-6 Luna takes 1,050,000 tokens and Gemini 3.5 Flash 1,048,576. Both support tool calling, reasoning, structured outputs, image input and file input; only Gemini 3.5 Flash also lists audio input and video input.
Side by side
| Spec | Gemini 3.5 Flash −10% | GPT-6 Luna −10% |
|---|---|---|
| Model | Gemini 3.5 Flashgoogle/ | GPT-6 Lunaopenai/ |
| Publisher | OpenAI | |
| Kind | Text, vision, audio & video | Text & vision |
| Context window | 1.05M tokens1,048,576 | 1.05M tokens1,050,000 |
| Input price | $1.35 / 1M tokens | $0.09 / 1M tokens |
| Output price | $8.10 / 1M tokens | $0.45 / 1M tokens |
| Cached input price | $0.15 / 1M tokens | $0.01 / 1M tokens |
| Cache write price | $1.583 / 1M tokens | $0.125 / 1M tokens |
| Web search price | $0.014 / search | $0.01 / search |
| Discount (vs official, top tier) | −10% | −10% |
| Inputs | text, images, files, audio and video | text, images and files |
| Outputs | text | text |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Structured outputs | Yes | Yes |
About these prices
Which should you choose?
- Choose GPT-6 Luna to spend less per token: 93% less for input and 94% less for output than Gemini 3.5 Flash.
- Context size does not separate them: both hold about 1.05M tokens.
- Choose Gemini 3.5 Flash if you need audio input and video input: GPT-6 Luna does not list them.
- Not sure? Call both with the same OceanToken API key and compare them on your own prompts; each request is billed per use from one prepaid balance.
Get API Key Gemini 3.5 Flash GPT-6 Luna
Frequently asked questions
Which is cheaper, Gemini 3.5 Flash or GPT-6 Luna?
GPT-6 Luna. GPT-6 Luna costs less per token than Gemini 3.5 Flash: $0.09 against $1.35 per 1M input tokens (93% less) and $0.45 against $8.10 per 1M output tokens (94% less). Both are 10% off their official price on OceanToken, for every account. The OceanToken console always shows the current price.
Which has the larger context window, Gemini 3.5 Flash or GPT-6 Luna?
GPT-6 Luna, by 1,424 tokens. Their context windows are almost the same size, about 1.05M tokens: GPT-6 Luna takes 1,050,000 tokens and Gemini 3.5 Flash 1,048,576.
Can I call both Gemini 3.5 Flash and GPT-6 Luna with one API key?
Yes. Both are on the OceanToken API at https://api.oceantoken.ai/v1: one API key and one prepaid balance call either model. Send the model id google/gemini-3.5-flash or openai/gpt-6-luna.
Models and publishers
Gemini 3.5 Flash · GPT-6 Luna · All Google models · All OpenAI models
More comparisons
DeepSeek V4.1 Flash vs Gemini 3.5 Flash · DeepSeek V4.1 Flash vs Gemini 3.5 Flash · DeepSeek V4 Pro vs Gemini 3.5 Flash · DeepSeek V3.2 vs Gemini 3.5 Flash · All comparisons