DeepSeek V4 Pro 0813 vs Kimi K3
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Pro 0813 starts 76% cheaper on input than Kimi K3 at list prices.
DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.627 / MTok
Best output$1.88 / MTok
Context1.05M
Providers15
Fastest measured0.76s° TTFT · 115 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Kimi K3
Moonshot AI · released Jul 16, 2026
Best input$2.60 / MTok
Best output$13.00 / MTok
Context1.05M
Providers15
Fastest measured0.61s° TTFT · 84 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 |  Alibaba | $0.627 | $1.88 | 1s° | 48° tok/s | 4/5 |
| DeepSeek V4 Pro 0813 |  DeepSeek | $0.66 | $1.98 | — | — | 0/5 |
| DeepSeek V4 Pro 0813 | GMIGMICloud | $1.12 | $3.37 | 3.2s° | 57° tok/s | 4/5 |
| Kimi K3 | SRSail Research | $2.60 | $13.00 | 1.5s° | 144° tok/s | 2/5 |
| Kimi K3 | MOMorph | $2.80 | $14.00 | 1.7s° | 17° tok/s | 1/5 |
| Kimi K3 |  DeepInfra | $2.85 | $14.25 | 2s° | 25° tok/s | 4/5 |
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