DeepSeek V4.1 Flash 1017 vs GLM 5.3
API pricing, context, and independently measured performance, side by side. DeepSeek V4.1 Flash 1017 starts 77% cheaper on input than GLM 5.3 at list prices.
DeepSeek V4.1 Flash 1017
DeepSeek · released Oct 17, 2026
Best input$0.016 / MTok
Best output$0.12 / MTok
Context1.05M
Providers44
Fastest measured0.21s° TTFT · 476 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
GLM 5.3
Z.ai · released Aug 18, 2026
Best input$0.07 / MTok
Best output$0.88 / MTok
Context1.05M
Providers51
Fastest measured0.49s° TTFT · 115 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | OPOpenInference | $0.016 | $1.44 | 1.2s° | 20° tok/s | — |
| DeepSeek V4.1 Flash 1017 |  Engy | $0.03 | $0.12 | — | — | — |
| DeepSeek V4.1 Flash 1017 |  Wafer | $0.038 | $0.50 | 0.31s° | 434° tok/s | — |
| GLM 5.3 | Wafer | $0.07 | $1.40 | 4.7s° | 117° tok/s | — |
| GLM 5.3 |  Relace | $0.07 | $4.38 | 1s° | 198° tok/s | — |
| GLM 5.3 |  InferenceNet | $0.08 | $3.60 | 1s° | 208° 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