DeepSeek V4 Flash 0423 vs Gemma 4 31B
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Flash 0423 starts 32% cheaper on input than Gemma 4 31B at list prices.
DeepSeek V4 Flash 0423
DeepSeek · released Apr 24, 2026
Best input$0.055 / MTok
Best output$0.109 / MTok
Context1.05M
Providers18
Fastest measured0.73s° TTFT · 138 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Gemma 4 31B
Google · released Apr 2, 2026
Best input$0.08 / MTok
Best output$0.34 / MTok
Context262K
Providers18
Fastest measured0.31s° TTFT · 205 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | BABaidu | $0.055 | $0.109 | 0.73s° | 138° tok/s | 5/5 |
| DeepSeek V4 Flash 0423 | STStreamLake | $0.056 | $0.112 | 2.2s° | 47° tok/s | 5/5 |
| DeepSeek V4 Flash 0423 | GMIGMICloud | $0.059 | $0.118 | 2.5s° | 105° tok/s | 5/5 |
| Gemma 4 31B | OPOpenInference | $0.08 | $0.35 | 2.3s° | 21° tok/s | 3/5 |
| Gemma 4 31B |  DeepInfra | $0.09 | $0.34 | 0.84s° | 56° tok/s | 5/5 |
| Gemma 4 31B | CWCoreWeave | $0.10 | $0.34 | 1.6s° | 38° tok/s | 5/5 |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) · 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