Gemini 3.8 Live Extended Thinking vs Schematron V2 Turbo

Specs, per-token pricing, and live benchmark scores — refreshed daily from our benchmark database.

Specs & pricing

Gemini 3.8 Live Extended ThinkingSchematron V2 Turbo
CompanyGoogle DeepMindInference Net
ReleasedSep 2026Sep 2026
Context window128K
Input /1M tokens$0.75$0.03
Output /1M tokens$3$0.15
Open weightsNoNo

Benchmarks

BenchmarkGemini 3.8 Live Extended ThinkingSchematron V2 Turbo
Speed (tok/s)7 tok/s

Scores come from published leaderboards and official model cards (sources listed on the benchmarks page) and refresh daily. Pricing via vendor pages and OpenRouter.