Google: Gemini 2.5 FlashReasoning

google
$0.6output / 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
oci
Official$0.15
$0.6
—-76.0% vs consensus
—
———
2
google
Official$0.3
$2.5
$0.02+0.0% vs consensus
493ms
reasoning 21.2s
221.0 tps——
3
vertex-ai
Official$0.3
$2.5
$0.03+0.0% vs consensus
—
———
4
deepinfra
Reseller$0.3
$2.5
—+0.0% vs consensus
—
———
5
deepinfra → google
Reseller$0.3
$2.5
—+0.0% vs consensus
—
———
6
lightningai
Reseller$0.3
$2.5
—+0.0% vs consensus
—
———
7
openrouter → google
Reseller$0.3
$2.5
—+0.0% vs consensus
—
———
8
openrouter → google-ai-studio
Reseller$0.3
$2.5
$0.03+0.0% vs consensus
—
———
9
openrouter → google-vertex
Reseller$0.3
$2.5
$0.03+0.0% vs consensus
—
———
10
vercel-ai-gateway → google
Reseller$0.3
$2.5
—+0.0% vs consensus
—
———
11
vertex-ai-language-models
Reseller$0.3
$2.5
$0.03+0.0% vs consensus
—
———
12
replicate → google
Reseller$2.5
$2.5
—+0.0% vs consensus
—
———
13
zeroeval → google
Disabled by zeroeval · disabled
Reseller$0.3
$2.5
—+0.0% vs consensus
—
———
Source ecosystem
Loading…