Gemini 3.1 Pro Preview vs GPT-6 Astra
API pricing, context, and independently measured performance, side by side. Gemini 3.1 Pro Preview starts 80% cheaper on input than GPT-6 Astra at list prices.
Gemini 3.1 Pro Preview
Google · released Feb 19, 2026
Best input$2.00 / MTok
Best output$12.00 / MTok
Context1.05M
Providers6
Fastest measured2.6s° TTFT · 285 tok/s
VisionToolsReasoningStructured outputPrompt caching
GPT-6 Astra
OpenAI · released Sep 4, 2026
Best input$10.00 / MTok
Best output$50.00 / MTok
Context1.05M
Providers5
Fastest measured4.3s° TTFT · 187 tok/s
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Gemini 3.1 Pro Preview |  Google | $1.00 | $6.00 | 2.6s° | 285° tok/s | — |
| Gemini 3.1 Pro Preview |  Google AI Studio | $1.00 | $6.00 | 5.3s° | 495° tok/s | — |
| GPT-6 Astra |  OpenAI | $5.00 | $25.00 | — | — | — |
| GPT-6 Astra |  Azure | $10.00 | $50.00 | 4.3s° | 187° tok/s | — |
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