Google: Gemini 3 Flash PreviewReasoning

google
$3output / 1M tokens

Best price — Output ($/1M tokens)

Markets

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

#ProviderClassInput $/MOutput $/MCache ($/M Read)vs consensusTTFTThroughputUptime 24hRequests 24h
1
google
Official$0.5
$3
$0.03+0.0% vs consensus
894ms
reasoning 7.9s
173.4 tps——
2
google-vertex
Official$0.5
$3
$0.05+0.0% vs consensus
—
———
3
gmi
Reseller$0.5
$3
—+0.0% vs consensus
—
———
4
gmi → google
Reseller$0.5
$3
—+0.0% vs consensus
—
———
5
lightningai
Reseller$0.5
$3
—+0.0% vs consensus
—
———
6
openrouter → google
Reseller$0.5
$3
$0.05+0.0% vs consensus
—
———
7
openrouter → google-ai-studio
Reseller$0.5
$3
$0.05+0.0% vs consensus
—
———
8
openrouter → google-vertex
Reseller$0.5
$3
$0.05+0.0% vs consensus
—
———
9
vertex-ai-language-models
Reseller$0.5
$3
$0.05+0.0% vs consensus
—
———
10
zeroeval → google
Reseller$0.5
$3
—+0.0% vs consensus
—
———
Source ecosystem
Loading…