DeepSeek V4.1 Flash 1017 vs GLM 5.3 Flash
API pricing, context, and independently measured performance, side by side. GLM 5.3 Flash starts 93% cheaper on input than DeepSeek V4.1 Flash 1017 at list prices.
DeepSeek V4.1 Flash 1017
DeepSeek · released Oct 17, 2026
Best input$0.07 / MTok
Best output$0.15 / MTok
Context1.05M
Providers33
Fastest measured0.69s° TTFT · 131 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
GLM 5.3 Flash
Z.ai · released Aug 26, 2026
Best input$0.005 / MTok
Best output$0.145 / MTok
Context1.05M
Providers39
Fastest measured0.38s° TTFT · 40 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | OPOpenInference | $0.07 | $0.50 | — | — | — |
| DeepSeek V4.1 Flash 1017 |  Relace | $0.07 | $0.50 | 0.69s° | 131° tok/s | — |
| DeepSeek V4.1 Flash 1017 |  InferenceNet | $0.08 | $0.50 | — | — | — |
| GLM 5.3 Flash | OPOpenInference | $0.005 | $0.199 | 0.38s° | 40° tok/s | — |
| GLM 5.3 Flash | Relace | $0.005 | $0.199 | 0.86s° | 134° tok/s | — |
| GLM 5.3 Flash |  StreamLake | $0.043 | $0.145 | 2s° | 71° 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