High-volume, cost-sensitive work
Choose DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 costs 26% less on a typical mix of three input tokens for every output token ($0.15 against $0.20 per million tokens).
DeepSeek V4 Flash 0731 vs GPT-6 Luna: price, context and capabilities
Choose DeepSeek V4 Flash 0731 for high-volume, cost-sensitive work and writing and code generation. Choose GPT-6 Luna for reused prompts and documents (RAG, agents), images as input and the latest release.
In short
- DeepSeek V4 Flash 0731 is 26% cheaper than GPT-6 Luna at the headline price ($0.1488 / 1M tokens vs $0.20 / 1M tokens).
- GPT-6 Luna reads more per request: 1.05M tokens against 1.05M.
- GPT-6 Luna is the newer model (Sep 22, 2026, against Jul 31, 2026).
- Only GPT-6 Luna offers vision, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Writing and code generation
Choose DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 charges $0.24 per million output tokens, against $0.50 for GPT-6 Luna. Output dominates the bill when answers are long.
Reused prompts and documents (RAG, agents)
Choose GPT-6 Luna
GPT-6 Luna charges $0.01 per million cached input tokens, against $0.02 for DeepSeek V4 Flash 0731.
Images as input
Choose GPT-6 Luna
GPT-6 Luna accepts images as input; DeepSeek V4 Flash 0731 does not.
Latest release
Choose GPT-6 Luna
GPT-6 Luna is the newer release (Sep 22, 2026, against Jul 31, 2026 for DeepSeek V4 Flash 0731).
Monthly cost at three volumes
| Volume | DeepSeek V4 Flash 0731 | GPT-6 Luna | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.18 | $0.23 | DeepSeek V4 Flash 0731, $0.05 less |
| Production: 20M input, 5M output tokens | $3.57 | $4.50 | DeepSeek V4 Flash 0731, $0.93 less |
| Scale: 500M input, 100M output tokens | $83.30 | $100.00 | DeepSeek V4 Flash 0731, $16.70 less |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| DeepSeek V4 Flash 0731 | GPT-6 Luna | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Category | Language models | Language models |
| Status | Generally available | Generally available |
| Headline price | $0.1488 / 1M tokens | $0.20 / 1M tokens |
| Input | $0.119 / 1M tokens | $0.10 / 1M tokens |
| Output | $0.238 / 1M tokens | $0.50 / 1M tokens |
| Cached input | $0.0238 / 1M tokens | $0.01 / 1M tokens |
| Context window | 1.05M | 1.05M |
| Max output | 944k | 128k |
| Released | Jul 31, 2026 | Sep 22, 2026 |
| Knowledge cutoff | No data | May 2026 |
| Licence | Proprietary | Proprietary |
| Capabilities | Reasoning, Tool calling, Structured output, Prompt caching | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | deepseek-v4-flash-0731 | gpt-6-luna |
Benchmarks side by side
Leader in bold.
| Benchmark | DeepSeek V4 Flash 0731 | GPT-6 Luna |
|---|---|---|
| Intelligence Index | No data | 38.1 |
| SciCode | No data | 54.6% |
| Humanity's Last Exam | No data | 38.5% |
| MMMU-Pro (visual reasoning) | No data | 79.7% |
| Long-context reasoning (AA-LCR) | No data | 83.3% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose DeepSeek V4 Flash 0731 or GPT-6 Luna?
Choose DeepSeek V4 Flash 0731 for high-volume, cost-sensitive work and writing and code generation. Choose GPT-6 Luna for reused prompts and documents (RAG, agents), images as input and the latest release.
Which is cheaper, DeepSeek V4 Flash 0731 or GPT-6 Luna?
DeepSeek V4 Flash 0731 is 26% cheaper than GPT-6 Luna at the headline price ($0.1488 / 1M tokens vs $0.20 / 1M tokens).
Which has the larger context window, DeepSeek V4 Flash 0731 or GPT-6 Luna?
GPT-6 Luna reads more per request: 1.05M tokens against 1.05M.
What is the difference between DeepSeek V4 Flash 0731 and GPT-6 Luna?
DeepSeek V4 Flash 0731 is made by DeepSeek and GPT-6 Luna by OpenAI. DeepSeek V4 Flash 0731 is 26% cheaper than GPT-6 Luna at the headline price ($0.1488 / 1M tokens vs $0.20 / 1M tokens). GPT-6 Luna reads more per request: 1.05M tokens against 1.05M. GPT-6 Luna is the newer model (Sep 22, 2026, against Jul 31, 2026). Only GPT-6 Luna offers vision, batch api.
How much do DeepSeek V4 Flash 0731 and GPT-6 Luna cost per month?
At 20 million input and 5 million output tokens a month, DeepSeek V4 Flash 0731 costs $3.57 and GPT-6 Luna costs $4.50, at standard rates.
Which is newer, DeepSeek V4 Flash 0731 or GPT-6 Luna?
GPT-6 Luna was released on Sep 22, 2026 and DeepSeek V4 Flash 0731 on Jul 31, 2026.