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. It is designed for fast inference and...
Model details →DeepSeek: DeepSeek V4 Flash 0423 vs OpenAI: GPT-5.6 Luna Pro (batch)
OpenAI: GPT-5.6 Luna Pro (batch) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
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. Learn more in OpenAI's docs: https://devel…
Model details →Side-by-side comparison
| Capability | DeepSeek: DeepSeek V4 Flash 0423 | OpenAI: GPT-5.6 Luna Pro (batch) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 1.0M | 1.1M | 🏆 OpenAI: GPT-5.6 Luna Pro (batch) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.14 | $0.10 | 🏆 OpenAI: GPT-5.6 Luna Pro (batch) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.28 | $0.60 | 🏆 DeepSeek: DeepSeek V4 Flash 0423 |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 OpenAI: GPT-5.6 Luna Pro (batch) |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is DeepSeek: DeepSeek V4 Flash 0423 better than OpenAI: GPT-5.6 Luna Pro (batch)?
OpenAI: GPT-5.6 Luna Pro (batch) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: DeepSeek V4 Flash 0423 and OpenAI: GPT-5.6 Luna Pro (batch)?
Input: $0.14 vs $0.10 per 1M tokens. Output: $0.28 vs $0.60 per 1M tokens.
What context windows do DeepSeek: DeepSeek V4 Flash 0423 and OpenAI: GPT-5.6 Luna Pro (batch) support?
DeepSeek: DeepSeek V4 Flash 0423 supports up to 1.0M tokens. OpenAI: GPT-5.6 Luna Pro (batch) supports up to 1.1M tokens.
Do both DeepSeek: DeepSeek V4 Flash 0423 and OpenAI: GPT-5.6 Luna Pro (batch) support tool calling?
DeepSeek: DeepSeek V4 Flash 0423: yes. OpenAI: GPT-5.6 Luna Pro (batch): yes.
Compare DeepSeek: DeepSeek V4 Flash 0423 with other models
vs Anthropic Claude Haiku Latestvs Anthropic Claude Sonnet Latestvs Anthropic: Claude Fable Latestvs Anthropic: Claude Opus Latest