Gemini 3.8 Flash
Google AIVotes and public adoption0 votes · 3 Adoption
Sign in to vote
As of 2026-10-22, the top-ranked models for High Throughput & Flash on ModelPriceLab are Gemini 3.8 Flash (Google), Claude Sonnet 5.5 (Anthropic) and Gemini 2.5 Pro (Google AI). Gemini 3.8 Flash lists at $0.75 input / $3.75 output per 1M tokens. The ranking weights pricing 50%, solution adoption 20%, editorial picks 15% and community votes 15%; it is a decision-signal ranking, not an independent benchmark, and no candidate has community votes yet.
Sub-second TTFT and high-concurrency models under $0.15/1M tokens for real-time APIs and ETL pipelines.Ranking computed 2026-10-22 (UTC)
Sign in to vote
Sign in to vote
Sign in to vote
Explore models with lowest listed token rates tailored for High Throughput & Flash, or compare head-to-head benchmark leaders.
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.