Compare models
GPT-6 Luna vs Gemini 3.8 Flash
| Spec | GPT-6 Luna | Gemini 3.8 Flash |
|---|---|---|
| Developer | OpenAI | Google DeepMind |
| Released | September 22, 2026 | September 2, 2026 |
| Status | Current | Current |
| Inputs | Text, Images | Text, Images, Audio, Video |
| Context window | 1.1M tokens | 1M tokens |
| Input price / 1M tokens | $0.10 | $0.75 |
| Output price / 1M tokens | $0.50 | $3.75 |
| Open weights | No | No |
| Access | OpenAI API | Gemini API, Vertex AI, Gemini app |
GPT-6 Luna in brief
GPT-6 Luna specs and pricing: OpenAI's lowest-cost GPT-6 model (September 2026) at $0.10/$0.50 per million tokens with a 1.05M-token context window.
- Very low price
- Fast responses
- Same ~1.05M-token context as the rest of the GPT-6 family
Gemini 3.8 Flash in brief
Gemini 3.8 Flash specs and pricing: Google's September 2026 model with a ~1M-token multimodal context at $0.75/$3.75 per million tokens (introductory), and comparisons.
- Low introductory price
- About 1M-token multimodal context
- Strong for long-horizon software engineering and agents
Which should you choose?
Choose GPT-6 Luna if you need: classification, extraction and routing at scale; chat features in consumer apps; sub-agents inside larger agent systems.
Choose Gemini 3.8 Flash if you need: cost-sensitive production apps; multimodal document and video analysis; high-volume agent workflows.
For most teams the best test is your own workload: run the same 20–50 real prompts through both models and compare quality, speed and cost. Benchmarks published by labs use different settings and rarely match everyday use.
Frequently asked questions
Which is cheaper, GPT-6 Luna or Gemini 3.8 Flash?
At list prices, GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens, compared with $0.75 and $3.75 for Gemini 3.8 Flash. Discounts for caching and batch processing can change the real cost.
Which has a bigger context window?
GPT-6 Luna can take in up to 1.1M tokens at once, versus 1M for Gemini 3.8 Flash.
Are GPT-6 Luna and Gemini 3.8 Flash open source?
GPT-6 Luna is closed: you use it through its developer’s apps or API. Gemini 3.8 Flash is closed: you use it through its developer’s apps or API.
Which model is newer?
GPT-6 Luna was released later, on September 22, 2026.
Sources
- OpenAI API models — OpenAI
- Gemini API pricing — Google
- Gemini API models — Google
Written by
Luka Kušec · Editor
Editor of SI.info. Writes about Super Intelligence, technology policy and the people building frontier models.