DeepSeek V4 Pro 0423 vs Kimi K2.6
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Pro 0423 starts 7% cheaper on input than Kimi K2.6 at list prices.
DeepSeek V4 Pro 0423
DeepSeek · released Apr 24, 2026
Best input$0.522 / MTok
Best output$1.04 / MTok
Context1.05M
Providers18
Fastest measured0.54s° TTFT · 175 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Kimi K2.6
Moonshot AI · released Apr 20, 2026
Best input$0.56 / MTok
Best output$2.36 / MTok
Context262K
Providers19
Fastest measured0.55s° TTFT · 199 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | STStreamLake | $0.522 | $1.04 | 4.8s° | 41° tok/s | 4/5 |
| DeepSeek V4 Pro 0423 | BABaidu | $0.524 | $1.05 | 0.66s° | 57° tok/s | 3/5 |
| DeepSeek V4 Pro 0423 | GMIGMICloud | $0.528 | $1.58 | 3.2s° | 58° tok/s | 4/5 |
| Kimi K2.6 | BABaidu | $0.56 | $2.36 | 0.87s° | 85° tok/s | 3/5 |
| Kimi K2.6 | DEDecart | $0.568 | $2.39 | 0.69s° | 197° tok/s | 3/5 |
| Kimi K2.6 | INInceptron | $0.57 | $3.41 | 0.82s° | 112° tok/s | 3/5 |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) · 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