DeepSeek V4 Pro 0423 vs Kimi K2.7 Code
API pricing, context, and independently measured performance, side by side. Kimi K2.7 Code starts 24% cheaper on input than DeepSeek V4 Pro 0423 at list prices.
DeepSeek V4 Pro 0423
DeepSeek · released Apr 24, 2026
Best input$0.87 / MTok
Best output$1.20 / MTok
Context1.05M
Providers18
Fastest measured0.52s° TTFT · 171 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Kimi K2.7 Code
Moonshot AI · released Jun 12, 2026
Best input$0.66 / MTok
Best output$3.00 / MTok
Context262K
Providers16
Fastest measured0.39s° TTFT · 114 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | DIDigitalOcean | $0.87 | $1.74 | 1.2s° | 5° tok/s | 5/5 |
| DeepSeek V4 Pro 0423 | STStreamLake | $0.951 | $1.90 | 4.8s° | 41° tok/s | 4/5 |
| DeepSeek V4 Pro 0423 | BABaidu | $0.96 | $1.92 | 0.66s° | 57° tok/s | 3/5 |
| Kimi K2.7 Code | INInceptron | $0.66 | $3.40 | 1.1s° | 165° tok/s | 5/5 |
| Kimi K2.7 Code |  DeepInfra | $0.68 | $3.40 | 0.4s° | 58° tok/s | 5/5 |
| Kimi K2.7 Code | CWCoreWeave | $0.71 | $3.50 | 0.61s° | 196° tok/s | 5/5 |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page