Compare GPT-5.6 Luna from OpenAI and DeepSeek V4 Flash 0423 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | GPT-5.6 Luna | DeepSeek V4 Flash 0423 |
|---|---|---|
| Input price | $0.20/M tokens | $0.05/M tokens |
| Output price | $1.20/M tokens | $0.45/M tokens |
| Context window | 1,050,000 tokens | 1,048,576 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | 71.4 | 52.0 |
| Agentic Index | 42.1 | 26.3 |
| Latency (p50) | 1.50 s | 0.61 s |
| Throughput (p50) | 137.0 tok/s | 71.0 tok/s |
| Provided by | OpenAI | DeepSeek |
| Model page | GPT-5.6 Luna model details, providers and pricing | DeepSeek V4 Flash 0423 model details, providers and pricing |
Benchmark data updated
GPT-5.6 Luna has the longer context window at 1,050,000 tokens, compared with 1,048,576 tokens for DeepSeek V4 Flash 0423.
GPT-5.6 Luna is faster on OpenRouter, generating a median 137.0 tokens per second compared with 71.0 tokens per second for DeepSeek V4 Flash 0423.
GPT-5.6 Luna scores higher on coding, with an Artificial Analysis Coding Index of 71.4 compared with 52.0 for DeepSeek V4 Flash 0423.