Google
Gemini 3.8 Flash
Gemini 3.8 Flash (high reasoning) by Google. High intelligence index (59), output throughput of 302 TPS, and native 1M context window with 90% prompt caching discount.
Intelligence
68.5 #127
Top 18% tier
Output speed
302.1 t/s
TTFT 180 ms · ITL 3.3 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 65536
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Gemini 3.8 Flash
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see Metodologia.
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 AIPontuações por fonte
Pontuações por categoria
Resultados de benchmarks
Detalhes do modelo
Data de lançamento
1 de set. de 2026
Parâmetros
Not disclosed
Licença
Proprietary
Janela de contexto
1,000,000 tokens
Preço de entrada
$0.75/M
Preço de saída
$3.75/M
Velocidade de saída
302 t/s
Tempo até o primeiro token
180 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)BibTeX
@misc{llmpodium2026gemini38flash,
title = {Benchmark Analysis and Intelligence Evaluation of Gemini 3.8 Flash},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/gemini-3-8-flash}
}More from Google
Modelos alternativos
Principais alternativas para Gemini 3.8 Flash com base em recursos, preço e benchmarks.
