DeepSeek V4 Flash 0731 vs GPT-6 Luna
Price and specs side by side · USD per 1M tokens · verified 2026-10-11
// side by side
| metric | DeepSeek V4 Flash 0731 | GPT-6 Luna |
|---|
| input / 1M | $0.06 | $0.10 |
| output / 1M | $0.18 | $0.50 |
| blended (3:1) | $0.09 | $0.20 |
| cache read / 1M | $0.015 | $0.01 |
| context | 1.05M | 1.05M |
| max output | 384K | 128K |
| input types | text | text · image · pdf |
| reasoning | yes | yes |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | yes | no |
| released | 2026-07-31 | 2026-09-22 |
| knowledge cutoff | 2025-05 | 2026-05-18 |
| lab | DeepSeek | OpenAI |
// monthly cost scenarios
| workload | tokens in / out | DeepSeek V4 Flash 0731 | GPT-6 Luna |
|---|
| Chatbot | 10M / 2M | $0.96 | $2.00 |
| RAG app | 50M / 5M | $3.90 | $7.50 |
| Coding agent | 20M / 10M | $3.00 | $7.00 |
// verdict
- DeepSeek V4 Flash 0731 is 55% cheaper than GPT-6 Luna on a blended 3:1 input/output basis.
- GPT-6 Luna has the larger context window (1.05M vs 1.05M tokens).
- Only GPT-6 Luna accepts image input.