Gemini 3.1 Pro Preview vs GPT-5.6 Terra
API pricing, context, and independently measured performance, side by side.
Gemini 3.1 Pro Preview
Google · released Feb 19, 2026
Best input$1.00 / MTok
Best output$6.00 / MTok
Context1.05M
Providers6
Fastest measured2.6s° TTFT · 285 tok/s
VisionToolsReasoningStructured outputPrompt caching
GPT-5.6 Terra
OpenAI · released Jul 9, 2026
Best input$1.00 / MTok
Best output$6.00 / MTok
Context1.05M
Providers7
Fastest measured2s° TTFT · 95 tok/s
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Gemini 3.1 Pro Preview |  Google AI Studio | $1.00 | $6.00 | 3.3s° | 671° tok/s | — |
| Gemini 3.1 Pro Preview |  Google | $1.00 | $6.00 | 2.6s° | 285° tok/s | — |
| GPT-5.6 Terra |  OpenAI | $1.00 | $6.00 | 2s° | 95° tok/s | — |
| GPT-5.6 Terra |  Azure | $2.00 | $12.00 | 6.5s° | 31° tok/s | — |
| GPT-5.6 Terra |  Amazon Bedrock | $2.20 | $13.20 | — | — | — |
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