AI model comparison
GPT-5.6 Luna Pro vs DeepSeek V4 Flash 0423
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
OpenAI
GPT-5.6 Luna Pro
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
- Input / 1M
- $0.20
- Output / 1M
- $1.20
- Context
- 1.05M
DeepSeek
DeepSeek V4 Flash 0423
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
- Input / 1M
- $0.01
- Output / 1M
- $1.28
- Context
- 1.05M
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
DeepSeek V4 Flash 0423
1.5x cheaper for a typical chat
Higher intelligence score
Tie
Not enough benchmark data
Larger context window
GPT-5.6 Luna Pro
1.05M vs 1.05M tokens
Newer release
GPT-5.6 Luna Pro
Released July 9, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-5.6 Luna ProNot availableDeepSeek V4 Flash 042324.4Coding index
GPT-5.6 Luna ProNot availableDeepSeek V4 Flash 042352Agentic index
GPT-5.6 Luna ProNot availableDeepSeek V4 Flash 042326.3Pricing
GPT-5.6 Luna Pro vs DeepSeek V4 Flash 0423 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-5.6 Luna Pro | DeepSeek V4 Flash 0423 |
|---|---|---|
| Input tokensPer 1M tokens | $0.20 | $0.01 |
| Output tokensPer 1M tokens | $1.20 | $1.28 |
| Cached input (read)Per 1M tokens | $0.02 | $0.01 |
| Cache writePer 1M tokens | $0.25 | Not available |
| Long-context pricingPer 1M tokens, for very long prompts | $0.40 in / $1.80 out above 272K | Same rate at any length |
| Web searchPer request | $0.01 | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
GPT-5.6 Luna Pro$1DeepSeek V4 Flash 0423$0.66Coding task
30K in, 4K out
GPT-5.6 Luna Pro$10.80$5.40 cachedDeepSeek V4 Flash 0423$5.42$5.42 cachedLong document summary
150K in, 2K out
GPT-5.6 Luna Pro$32.40$5.40 cachedDeepSeek V4 Flash 0423$4.05$4.05 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-5.6 Luna Pro | DeepSeek V4 Flash 0423 |
|---|---|---|
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 128K tokens | 944K tokens |
| Input types | File, Image, Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Max, Extra high, High, Medium, Low, None | Extra high, High |
| Default reasoning effort | Medium | High |
| Release date | July 9, 2026 | April 24, 2026 |
Features
Supported features
API features available for each model.
| Metric | GPT-5.6 Luna Pro | DeepSeek V4 Flash 0423 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Not supported | Supported |
| Stop sequences | Not supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
GPT-5.6 Luna ProView full model details- GPT-5.6 Luna Pro vs DeepSeek V4.1 Flash
- GPT-5.6 Luna Pro vs GLM 5.3 Flash
- GPT-5.6 Luna Pro vs Hy4 preview
- GPT-5.6 Luna Pro vs GPT-6 Luna
- GPT-5.6 Luna Pro vs DeepSeek V4 Flash 0731
- GPT-5.6 Luna Pro vs GPT-5.6 Luna
- GPT-5.6 Luna Pro vs MiniMax M3
- GPT-5.6 Luna Pro vs GPT-5.4 Nano
- GPT-5.6 Luna Pro vs GPT-4.1 Mini
DeepSeek V4 Flash 0423View full model details- DeepSeek V4 Flash 0423 vs DeepSeek V4.1 Flash
- DeepSeek V4 Flash 0423 vs GLM 5.3 Flash
- DeepSeek V4 Flash 0423 vs MiMo-V2.6-Flash
- DeepSeek V4 Flash 0423 vs Hy4 preview
- DeepSeek V4 Flash 0423 vs GPT-6 Luna
- DeepSeek V4 Flash 0423 vs DeepSeek V4 Flash 0731
- DeepSeek V4 Flash 0423 vs Claude Opus 5.5
- DeepSeek V4 Flash 0423 vs GLM 5.3
- DeepSeek V4 Flash 0423 vs Step 5 Preview
- DeepSeek V4 Flash 0423 vs Gemini 3.8 Flash
- DeepSeek V4 Flash 0423 vs Hy3
- DeepSeek V4 Flash 0423 vs MiniMax M3
- DeepSeek V4 Flash 0423 vs Gemini 3 Flash Preview
- DeepSeek V4 Flash 0423 vs Solar Mini 4
- DeepSeek V4 Flash 0423 vs MiMo-V2.5
- DeepSeek V4 Flash 0423 vs DeepSeek V4 Pro 0423
- DeepSeek V4 Flash 0423 vs Solar Pro 4
- DeepSeek V4 Flash 0423 vs DeepSeek V3.2
- DeepSeek V4 Flash 0423 vs Gemini 3.5 Flash Lite
- DeepSeek V4 Flash 0423 vs GLM 5.3 FlashX
- DeepSeek V4 Flash 0423 vs Step 3.7 Flash
- DeepSeek V4 Flash 0423 vs MiMo-V2.5-Pro
- DeepSeek V4 Flash 0423 vs Kimi K2.6
- DeepSeek V4 Flash 0423 vs GPT-5.4 Mini
- DeepSeek V4 Flash 0423 vs GPT-5 Mini
- DeepSeek V4 Flash 0423 vs GPT-5.4 Nano
- DeepSeek V4 Flash 0423 vs Qwen3.7 Plus
- DeepSeek V4 Flash 0423 vs Qwen3.6 35B A3B
- DeepSeek V4 Flash 0423 vs MiniMax M2.7
- DeepSeek V4 Flash 0423 vs GLM 4.7
- DeepSeek V4 Flash 0423 vs Ling 3.0 Flash VL
- DeepSeek V4 Flash 0423 vs GLM 5
- DeepSeek V4 Flash 0423 vs Kimi K2.7 Code
- DeepSeek V4 Flash 0423 vs Qwen3.5 397B A17B
- DeepSeek V4 Flash 0423 vs Kimi K2.5
- DeepSeek V4 Flash 0423 vs Grok 4.3
- DeepSeek V4 Flash 0423 vs Grok Build 0.1
- DeepSeek V4 Flash 0423 vs Muse Glimmer 30B
- DeepSeek V4 Flash 0423 vs Qwen3.6 Plus
- DeepSeek V4 Flash 0423 vs GLM 5 Turbo
- DeepSeek V4 Flash 0423 vs GLM 5.1
- DeepSeek V4 Flash 0423 vs Nemotron 3 Ultra
- DeepSeek V4 Flash 0423 vs Grok 4.20
- DeepSeek V4 Flash 0423 vs Inkling Small
- DeepSeek V4 Flash 0423 vs GPT-5.1
- DeepSeek V4 Flash 0423 vs Inkling
- DeepSeek V4 Flash 0423 vs GPT-5.1-Codex
- DeepSeek V4 Flash 0423 vs GLM 4.6
- DeepSeek V4 Flash 0423 vs GLM 5V Turbo
- DeepSeek V4 Flash 0423 vs GPT-5
- DeepSeek V4 Flash 0423 vs Qwen3.5-27B
- DeepSeek V4 Flash 0423 vs MiniMax M2.5
- DeepSeek V4 Flash 0423 vs Ling 3.0 Flash Fin
- DeepSeek V4 Flash 0423 vs Qwen3.5-35B-A3B
- DeepSeek V4 Flash 0423 vs Kimi K2 Thinking
- DeepSeek V4 Flash 0423 vs Qwen3.6 27B
- DeepSeek V4 Flash 0423 vs MiniMax M2.1
- DeepSeek V4 Flash 0423 vs GPT-5.1-Codex-Mini
- DeepSeek V4 Flash 0423 vs LongCat 2.0
- DeepSeek V4 Flash 0423 vs MiniMax M2
- DeepSeek V4 Flash 0423 vs DeepSeek V3.1 Terminus
Our take
DeepSeek V4 Flash 0423 is 1.5x cheaper for a typical chat. GPT-5.6 Luna Pro has the larger context window (1.05M vs 1.05M tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is GPT-5.6 Luna Pro or DeepSeek V4 Flash 0423 cheaper?
DeepSeek V4 Flash 0423 is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V4 Flash 0423 costs $0.01 per 1M input tokens and $1.28 per 1M output tokens, while GPT-5.6 Luna Pro costs $0.20 per 1M input tokens and $1.20 per 1M output tokens.
Which has a bigger context window, GPT-5.6 Luna Pro or DeepSeek V4 Flash 0423?
GPT-5.6 Luna Pro supports up to 1.05M tokens of context, compared with 1.05M for DeepSeek V4 Flash 0423.
Can I use GPT-5.6 Luna Pro and DeepSeek V4 Flash 0423 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-5.6 Luna Pro and DeepSeek V4 Flash 0423 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-5.6 Luna Pro and DeepSeek V4 Flash 0423 at the same time. Compare the answers side by side and keep the best one.