Compare DeepSeek V4.1 Flash from DeepSeek and GPT Luna Latest from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.


DeepSeek V4.1 Flash and GPT Luna Latest are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
DeepSeek V4.1 Flash, from DeepSeek, has a 1,048,576-token context window and is priced at $0.0108/M tokens input, $1/M tokens output on OpenRouter.
GPT Luna Latest, from OpenAI, has a 1,050,000-token context window and is priced at $0.10/M tokens input, $0.50/M tokens output on OpenRouter.
| Attribute | DeepSeek V4.1 Flash | GPT Luna Latest |
|---|---|---|
| Input price | $0.0108/M tokens | $0.10/M tokens |
| Output price | $1/M tokens | $0.50/M tokens |
| Context window | 1,048,576 tokens | 1,050,000 tokens |
| Intelligence Index | Not available | 27.8 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 1.31 s | 2.66 s |
| Throughput (p50) | 80.0 tok/s | 79.0 tok/s |
Benchmark data updated
GPT Luna Latest has the longer context window at 1,050,000 tokens, compared with 1,048,576 tokens for DeepSeek V4.1 Flash.
DeepSeek V4.1 Flash is faster on OpenRouter, generating a median 80.0 tokens per second compared with 79.0 tokens per second for GPT Luna Latest.