Compare Kimi K3 from moonshotai and DeepSeek V4 Pro 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.
Kimi K3 and DeepSeek V4 Pro 0423 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Kimi K3, from moonshotai, has a 1,048,576-token context window and is priced at $0.47/M tokens input, $13/M tokens output on OpenRouter.
DeepSeek V4 Pro 0423, from DeepSeek, has a 1,048,576-token context window and is priced at $0.2524/M tokens input, $4.20/M tokens output on OpenRouter.
| Kimi K3 | DeepSeek V4 Pro 0423 | |
|---|---|---|
| Input price | $0.47/M tokens | $0.2524/M tokens |
| Output price | $13/M tokens | $4.20/M tokens |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Intelligence Index | 43.6 | 30.1 |
| Coding Index | 76.2 | 58.7 |
| Agentic Index | 50.0 | Not available |
| Latency (p50) | 2.15 s | 0.90 s |
| Throughput (p50) | 42.0 tok/s | 99.0 tok/s |
DeepSeek V4 Pro 0423 is cheaper than Kimi K3 on OpenRouter: DeepSeek V4 Pro 0423 costs $0.2524/M tokens input and $4.20/M tokens output, while Kimi K3 costs $0.47/M tokens input and $13/M tokens output.
Kimi K3 and DeepSeek V4 Pro 0423 have the same context window of 1,048,576 tokens.
DeepSeek V4 Pro 0423 is faster on OpenRouter, generating a median 99.0 tokens per second compared with 42.0 tokens per second for Kimi K3.
Kimi K3 scores higher on coding, with an Artificial Analysis Coding Index of 76.2 compared with 58.7 for DeepSeek V4 Pro 0423.