Skip to content
llmprice

Gemini 3 Flash Preview

Updated Sep 11, 2026

gemini-flash1.0M context66k max outputreleased Dec 17, 2025ReasoningTool calling
Cheapest input
$0.07
Cheapest output
$0.43
Official (Google)
$3
output per 1M tokens
Providers
29
offering this model
Spread
8.7×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
QiHangCheapest$0.07Cheapest$0.431.0M
Kilo Gateway$0.25$1.5$0.025$0.04171.0M
Poe$0.4$2.4$0.041.0M
302.AI$0.5$31.0M
Abacus$0.5$3$0.051.0M
AIHubMix$0.5$3$0.051.0M
CrossModel$0.5$3$0.05$0.51.0M
Databricks$0.5$3$0.051.0M
Eden AI$0.5$3$0.05$0.08331.0M
Eden AI$0.5$3$0.05$0.08331.0M
FrogBot$0.5$3$0.051.0M
Google$0.5$3$0.051.0M
Vertex$0.5$3$0.051.0M
Jiekou.AI$0.5$31.0M
DevPass (LLM Gateway)$0.5$3$0.051.0M
LLM Gateway$0.5$3$0.051.0M
LLM Gateway$0.5$3$0.051.0M
Merge Gateway$0.5$3$0.051.0M
NanoGPT$0.5$3$0.051.0M
Neon$0.5$3$0.051.0M
Ofox$0.5$3$0.05$11.0M
OpenCode Zen$0.5$3$0.051.0M
OpenRouter$0.5$3$0.05$0.08331.0M
Opper$0.5$3$0.051.0M
OrcaRouter$0.5$3$0.051.0M
Perplexity Agent$0.5$3$0.051.0M
Pioneer$0.5$3$0.05$0.08331.0M
Vercel AI Gateway$0.5$3$0.051.0M
ZenMux$0.5$3$0.05$11.0M
Venice AI$0.7$3.75$0.07256k

Other gemini-flash models