Google
Gemini 3.8 Flash (Low Reasoning)
Low reasoning effort variant of Gemini 3.8 Flash optimized for sub-150ms TTFT and maximum throughput.
Intelligence
62.0 #258
Top 37% tier
Output speed
340 t/s
TTFT 140 ms · ITL 2.9 ms/tok
Blended price (3:1)
$1.5 /1M
In $0.75/M · Out $3.75/M
Context
1M
≈ 2,500 A4 pages · max out 32768
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Gemini 3.8 Flash (Low Reasoning)
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see 평가 방법.
API deployment
Compare hosts & latency
Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Groq
Cerebras
Together AI
DeepInfra
Fireworks AI
AWS Bedrock
Azure AI출처별 점수
카테고리별 점수
벤치마크 결과
모델 상세 정보
출시일
2026년 9월 1일
파라미터 수
Not disclosed
라이선스
Proprietary
컨텍스트 창
1,000,000 tokens
입력 가격
$0.75/M
출력 가격
$3.75/M
출력 속도
340 t/s
첫 토큰 생성 시간
140 ms
Estimated monthly bill
Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...
Cite & embed
GitHub Markdown badge
[](https://llmpodium.com/models/gemini-3-8-flash-low)BibTeX
@misc{llmpodium2026gemini38flashlow,
title = {Benchmark Analysis and Intelligence Evaluation of Gemini 3.8 Flash (Low Reasoning)},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/gemini-3-8-flash-low}
}More from Google
대체 모델
성능, 가격 및 벤치마크 점수를 기반으로 한 Gemini 3.8 Flash (Low Reasoning)의 주요 대체 모델.