Compare DeepSeek V4 Pro 0423 from DeepSeek and Grok 4.6 from SpaceXAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | DeepSeek V4 Pro 0423 | Grok 4.6 |
|---|---|---|
| Input price | $0.8719/M tokens | $2/M tokens |
| Output price | $1.744/M tokens | $6/M tokens |
| Context window | 1,048,576 tokens | 500,000 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | 58.7 | 76.8 |
| Agentic Index | Not available | 53.0 |
| Latency (p50) | 1.72 s | 2.00 s |
| Throughput (p50) | 37.0 tok/s | 68.0 tok/s |
| Provided by | DeepSeek | SpaceXAI |
| Model page | DeepSeek V4 Pro 0423 model details, providers and pricing | Grok 4.6 model details, providers and pricing |
Benchmark data updated
DeepSeek V4 Pro 0423 has the longer context window at 1,048,576 tokens, compared with 500,000 tokens for Grok 4.6.
Grok 4.6 is faster on OpenRouter, generating a median 68.0 tokens per second compared with 37.0 tokens per second for DeepSeek V4 Pro 0423.
Grok 4.6 scores higher on coding, with an Artificial Analysis Coding Index of 76.8 compared with 58.7 for DeepSeek V4 Pro 0423.