ModelPickr

Models / Google / Gemini 3 Flash Preview

Google · gemini-flash

Gemini 3 Flash Preview

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

$0.50 in · $3.00 out

per 1M tokens · first-party price. Reference price from Google, the lab's own listing.

Provider input prices run from $0.25 to $0.70 per 1M tokens. Output prices run from $1.50 to $3.75.

Context
1,048,576
Max output
65,536
Cache read
$0.05
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Dec 17, 2025
Updated in source
Dec 17, 2025
Knowledge
2025-01
Providers
21

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Kilo Gateway$0.25$1.50$0.025$0.042—
Abacus$0.50$3.00$0.05——
CrossModel$0.50$3.00$0.05$0.50—
Databricks$0.50$3.00$0.05——
DevPass$0.50$3.00$0.05——
Eden AI$0.50$3.00$0.05$0.083—
Googlereference$0.50$3.00$0.05——
LLM Gateway$0.50$3.00$0.05——
Merge Gateway$0.50$3.00$0.05——
NanoGPT$0.50$3.00$0.05——
Neon$0.50$3.00$0.05——
Ofox$0.50$3.00$0.05$1.00—
OpenRouter$0.50$3.00$0.05$0.083—
Opper$0.50$3.00$0.05——
OrcaRouter$0.50$3.00$0.05——
Pioneer$0.50$3.00$0.05$0.083—
Prime Inference$0.50$3.00———
Tempr Gateway$0.50$3.00$0.05——
Vertex$0.50$3.00$0.05—beta
Venice AI$0.70$3.75$0.07——
AnyAPI—————

Jobs this model qualifies for