DeepSeek V4 Pro 0813 vs Gemini 3.1 Pro Preview
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Pro 0813 starts 95% cheaper on input than Gemini 3.1 Pro Preview at list prices.
DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.10 / MTok
Best output$0.396 / MTok
Context1.05M
Providers21
Fastest measured0.53s° TTFT · 109 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Gemini 3.1 Pro Preview
Google · released Feb 19, 2026
Best input$2.00 / MTok
Best output$12.00 / MTok
Context1.05M
Providers6
Fastest measured2.9s° TTFT · 495 tok/s
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | $0.10 | $8.00 | 1.9s° | 46° tok/s | — | |
| DeepSeek V4 Pro 0813 | $0.111 | $4.44 | 0.58s° | 135° tok/s | — | |
| DeepSeek V4 Pro 0813 | $0.132 | $0.396 | 1.6s° | 48° tok/s | — | |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 3.3s° | 267° tok/s | — | |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 2.9s° | 495° tok/s | — |
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