DeepSeek V4 Pro 0813 vs Kimi K2.6
API pricing, context, and independently measured performance, side by side. Kimi K2.6 starts 19% cheaper on input than DeepSeek V4 Pro 0813 at list prices.
DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.66 / MTok
Best output$1.98 / MTok
Context1.05M
Providers19
Fastest measured0.67s° TTFT · 90 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Kimi K2.6
Moonshot AI · released Apr 20, 2026
Best input$0.537 / MTok
Best output$2.26 / MTok
Context262K
Providers21
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 0813 |  DeepSeek | $0.66 | $1.98 | — | — | 0/5 |
| DeepSeek V4 Pro 0813 |  Novita | $1.11 | $3.33 | 1.4s° | 68° tok/s | 4/5 |
| DeepSeek V4 Pro 0813 | BABaidu | $1.12 | $3.36 | — | — | — |
| Kimi K2.6 | BABaidu | $0.537 | $2.26 | 0.87s° | 85° tok/s | 3/5 |
| Kimi K2.6 | DEDecart | $0.537 | $2.26 | 0.69s° | 197° tok/s | 3/5 |
| Kimi K2.6 | INInceptron | $0.56 | $3.39 | 0.82s° | 112° tok/s | 3/5 |
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