DeepSeek V4 Flash 0731 vs gpt-oss-120b
API pricing, context, and independently measured performance, side by side. gpt-oss-120b starts 25% cheaper on input than DeepSeek V4 Flash 0731 at list prices.
DeepSeek V4 Flash 0731
DeepSeek · released Jul 31, 2026
Best input$0.04 / MTok
Best output$0.08 / MTok
Context1.31M
Providers30
Fastest measured0.48s° TTFT · 65 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
gpt-oss-120b
OpenAI · released Aug 5, 2025
Best input$0.03 / MTok
Best output$0.17 / MTok
Context131K
Providers20
Fastest measured0.21s° TTFT · 366 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | RERelace | $0.04 | $0.08 | 0.49s° | 65° tok/s | 5/5 |
| DeepSeek V4 Flash 0731 | OPOpenInference | $0.04 | $0.13 | 14.9s° | 13° tok/s | 3/5 |
| DeepSeek V4 Flash 0731 | DEDecart | $0.064 | $0.128 | 0.65s° | 51° tok/s | 4/5 |
| gpt-oss-120b | CWCoreWeave | $0.03 | $0.17 | 0.76s° | 51° tok/s | 3/5 |
| gpt-oss-120b |  DeepInfra | $0.037 | $0.17 | 0.55s° | 54° tok/s | 4/5 |
| gpt-oss-120b | AKAkashML | $0.037 | $0.49 | 1.6s° | 68° tok/s | 4/5 |
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