DeepSeek V4 Pro 0813 vs GLM 5.3 FlashX
API pricing, context, and independently measured performance, side by side. GLM 5.3 FlashX starts 36% cheaper on input than DeepSeek V4 Pro 0813 at list prices.
DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.578 / MTok
Best output$1.73 / MTok
Context1.05M
Providers23
Fastest measured0.59s° TTFT · 102 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
GLM 5.3 FlashX
Z.ai · released Sep 18, 2026
Best input$0.37 / MTok
Best output$1.25 / MTok
Context1.05M
Providers1
Fastest measured—
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | BABaidu | $0.578 | $1.73 | 0.81s° | 55° tok/s | — |
| DeepSeek V4 Pro 0813 |  DeepSeek | $0.66 | $1.98 | — | — | 0/5 |
| DeepSeek V4 Pro 0813 | IOIonstream | $0.70 | $2.88 | — | — | — |
| GLM 5.3 FlashX |  Z.AI | $0.37 | $1.25 | — | — | — |
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