DeepSeek V4 Flash 0731 vs gpt-oss-120b
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Flash 0731 starts 30% cheaper on input than gpt-oss-120b at list prices.
DeepSeek V4 Flash 0731
DeepSeek · released Jul 31, 2026
Best input$0.021 / MTok
Best output$0.134 / MTok
Context1.05M
Providers28
Fastest measured0.39s° TTFT · 210 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
gpt-oss-120b
OpenAI · released Aug 5, 2025
Best input$0.03 / MTok
Best output$0.15 / MTok
Context131K
Providers26
Fastest measured0.26s° TTFT · 227 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 |  Reka | $0.021 | $0.528 | 0.81s° | 112° tok/s | — |
| DeepSeek V4 Flash 0731 |  Relace | $0.057 | $0.134 | 0.7s° | 127° tok/s | 5/5 |
| DeepSeek V4 Flash 0731 |  DeepInfra | $0.06 | $0.18 | 0.5s° | 68° tok/s | — |
| gpt-oss-120b |  Near AI | $0.03 | $0.15 | 1.3s° | 74° tok/s | — |
| gpt-oss-120b |  Venice | $0.03 | $0.15 | — | — | — |
| gpt-oss-120b |  CoreWeave | $0.03 | $0.17 | 0.68s° | 33° tok/s | 3/5 |
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