DeepSeek V4 Pro 0813 vs GPT-6.1 Sol
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Pro 0813 starts 95% cheaper on input than GPT-6.1 Sol at list prices.
DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.11 / MTok
Best output$1.48 / MTok
Context1.05M
Providers22
Fastest measured0.57s° TTFT · 116 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
GPT-6.1 Sol
OpenAI · released Sep 29, 2026
Best input$2.00 / MTok
Best output$10.00 / MTok
Context1.05M
Providers7
Fastest measured—
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 |  Relace | $0.11 | $2.70 | — | — | — |
| DeepSeek V4 Pro 0813 |  Wafer | $0.12 | $4.20 | — | — | — |
| DeepSeek V4 Pro 0813 |  Ionstream | $0.149 | $1.48 | 1.9s° | 27° tok/s | — |
| GPT-6.1 Sol |  Azure | $2.00 | $10.00 | — | — | — |
| GPT-6.1 Sol |  OpenAI | $2.00 | $10.00 | — | — | — |
| GPT-6.1 Sol |  Amazon Bedrock | $2.20 | $11.00 | — | — | — |
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