High-volume, cost-sensitive work
Choose GPT-6 Luna
GPT-6 Luna costs 38% less on a typical mix of three input tokens for every output token ($0.20 against $0.32 per million tokens).
DeepSeek V4 Flash Vision Exp vs GPT-6 Luna: price, context and capabilities
Choose DeepSeek V4 Flash Vision Exp for reused prompts and documents (RAG, agents). Choose GPT-6 Luna for high-volume, cost-sensitive work, writing and code generation and the latest release.
In short
- GPT-6 Luna is 38% cheaper than DeepSeek V4 Flash Vision Exp at the headline price ($0.20 / 1M tokens vs $0.3234 / 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 Aug 21, 2026).
- Only GPT-6 Luna offers 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 GPT-6 Luna
GPT-6 Luna charges $0.50 per million output tokens, against $0.65 for DeepSeek V4 Flash Vision Exp. Output dominates the bill when answers are long.
Reused prompts and documents (RAG, agents)
Choose DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp charges <$0.01 per million cached input tokens, against $0.01 for GPT-6 Luna.
Latest release
Choose GPT-6 Luna
GPT-6 Luna is the newer release (Sep 22, 2026, against Aug 21, 2026 for DeepSeek V4 Flash Vision Exp).
Monthly cost at three volumes
| Volume | DeepSeek V4 Flash Vision Exp | GPT-6 Luna | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.38 | $0.23 | GPT-6 Luna, $0.15 less |
| Production: 20M input, 5M output tokens | $7.55 | $4.50 | GPT-6 Luna, $3.05 less |
| Scale: 500M input, 100M output tokens | $172.48 | $100.00 | GPT-6 Luna, $72.48 less |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| DeepSeek V4 Flash Vision Exp | GPT-6 Luna | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Category | Language models | Language models |
| Status | Preview | Generally available |
| Headline price | $0.3234 / 1M tokens | $0.20 / 1M tokens |
| Input | $0.2156 / 1M tokens | $0.10 / 1M tokens |
| Output | $0.6468 / 1M tokens | $0.50 / 1M tokens |
| Cached input | $0.0069 / 1M tokens | $0.01 / 1M tokens |
| Context window | 1.05M | 1.05M |
| Max output | 262k | 128k |
| Released | Aug 21, 2026 | Sep 22, 2026 |
| Knowledge cutoff | No data | May 2026 |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Prompt caching | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | deepseek-v4-flash-vision-exp | gpt-6-luna |
Benchmarks side by side
Leader in bold.
| Benchmark | DeepSeek V4 Flash Vision Exp | 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 Vision Exp or GPT-6 Luna?
Choose DeepSeek V4 Flash Vision Exp for reused prompts and documents (RAG, agents). Choose GPT-6 Luna for high-volume, cost-sensitive work, writing and code generation and the latest release.
Which is cheaper, DeepSeek V4 Flash Vision Exp or GPT-6 Luna?
GPT-6 Luna is 38% cheaper than DeepSeek V4 Flash Vision Exp at the headline price ($0.20 / 1M tokens vs $0.3234 / 1M tokens).
Which has the larger context window, DeepSeek V4 Flash Vision Exp 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 Vision Exp and GPT-6 Luna?
DeepSeek V4 Flash Vision Exp is made by DeepSeek and GPT-6 Luna by OpenAI. GPT-6 Luna is 38% cheaper than DeepSeek V4 Flash Vision Exp at the headline price ($0.20 / 1M tokens vs $0.3234 / 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 Aug 21, 2026). Only GPT-6 Luna offers batch api.
How much do DeepSeek V4 Flash Vision Exp and GPT-6 Luna cost per month?
At 20 million input and 5 million output tokens a month, DeepSeek V4 Flash Vision Exp costs $7.55 and GPT-6 Luna costs $4.50, at standard rates.
Which is newer, DeepSeek V4 Flash Vision Exp or GPT-6 Luna?
GPT-6 Luna was released on Sep 22, 2026 and DeepSeek V4 Flash Vision Exp on Aug 21, 2026.