DeepSeek-V4.1-Flash vs GPT-6 Luna
At 6,000 chat requests per month (1,500 in / 400 out), GPT-6 Luna costs $2.10 and DeepSeek-V4.1-Flash costs $5.58 — roughly 2.7× the spend.
| Spec | DeepSeek-V4.1-Flash | GPT-6 Luna |
|---|---|---|
| Vendor | DeepSeek | OpenAI |
| Input / 1M tokens | $0.300 | $0.100 |
| Output / 1M tokens | $1.20 | $0.500 |
| Cached input / 1M | $0.0060 | $0.010 |
| Context window | 1M tokens | 1.1M tokens |
| Max output | 384K tokens | 128K tokens |
| Input modalities | text, image | text, image |
| Released | — | — |
| Cost per 1M cached reads | $0.0060 | $0.010 |
Published list prices, last verified Oct 15, 2026. Source links are on each model's page.
Cost at three workloads
| Workload | DeepSeek-V4.1-Flash | GPT-6 Luna | Difference |
|---|---|---|---|
| Customer-support reply (1,500 in / 400 out) | $0.0009 | $0.0004 | GPT-6 Luna cheaper by $0.0006 |
| Document summary (20,000 in / 1,000 out) | $0.0072 | $0.0025 | GPT-6 Luna cheaper by $0.0047 |
| Code review pass (8,000 in / 1,500 out) | $0.0042 | $0.0016 | GPT-6 Luna cheaper by $0.0026 |
Which one fits your workload
- Long context: GPT-6 Luna accepts more — 1.1M versus 1M tokens. If your retrieved context regularly exceeds 1M, only one of these will hold it.
- Long answers: GPT-6 Luna has the lower output price ($0.500 vs $1.20 per million), which matters most when answers are long.
- High-volume, short answers: GPT-6 Luna is cheaper on input ($0.100 vs $0.300 per million).
- Caching: at least one of these vendors publishes a discounted cached-input rate; if you resend the same system prompt and context, model the cache-hit rate or you will overestimate cost.
This comparison uses published price and specification data only. It does not rank output quality — run your own evaluation on your own prompts before switching a production default.