Models/DeepSeek V4 Pro 0813 vs Qwen4 Max

DeepSeek V4 Pro 0813 vs Qwen4 Max

API pricing, context, and independently measured performance, side by side. DeepSeek V4 Pro 0813 starts 93% cheaper on input than Qwen4 Max at list prices.

DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.10 / MTok
Best output$1.98 / MTok
Context1.05M
Providers26
Fastest measured0.53s° TTFT · 109 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Qwen4 Max
Qwen · released Nov 16, 2026
Best input$1.50 / MTok
Best output$4.50 / MTok
Context1M
Providers1
Fastest measured—
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
MODELPROVIDERINPUTOUTPUTTTFTTPSSMOKE
DeepSeek V4 Pro 0813Relace logoRelace$0.10$8.001.9s°46° tok/s—
DeepSeek V4 Pro 0813Wafer logoWafer$0.111$4.440.58s°135° tok/s—
DeepSeek V4 Pro 0813StreamLake logoStreamLake$0.66$1.981.7s°59° tok/s5/5
Qwen4 MaxAlibaba logoAlibaba$1.50$4.50———
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
All 26 providers for DeepSeek V4 Pro 0813All 1 providers for Qwen4 MaxOpen in comparator