ModelPickr

Models / Google / Gemini 3.6 Flash

Google · gemini-flash

Gemini 3.6 Flash

Fast Gemini model balancing multimodal reasoning, tool use, and cost

$0.75 in · $3.75 out

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

Provider input prices run from $0.38 to $1.95 per 1M tokens. Output prices run from $1.88 to $9.75.

Context
1,048,576
Max output
65,536
Cache read
$0.075
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Jul 21, 2026
Updated in source
Jul 21, 2026
Knowledge
2026-03
Providers
29

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$0.38$1.88$0.038$0.021—
Cortecs$0.75$3.75$0.075$0.038—
CrossModel$0.75$3.75$0.075$0.75—
DevPass$0.75$3.75$0.075$0.083—
Eden AI$0.75$3.75$0.075$0.042—
GitHub Copilot$0.75$3.75$0.075——
Googlereference$0.75$3.75$0.075——
LLM Gateway$0.75$3.75$0.075$0.083—
NanoGPT$0.75$3.75$0.075$0.042—
Ofox$0.75$3.75$0.075$0.042—
OpenRouter$0.75$3.75$0.075$0.042—
Tempr Gateway$0.75$3.75$0.075——
Vercel AI Gateway$0.75$3.75$0.075——
Vertex$0.75$3.75$0.075—deprecated
Venice AI$0.94$4.69$0.094——
302.AI$1.50$7.50———
Abacus$1.50$7.50$0.15——
AIHubMix$1.50$7.50$0.15——
Impossibl$1.50$7.50$0.15——
Merge Gateway$1.50$7.50$0.15——
Neon$1.50$7.50$0.15——
OpenCode$1.50$7.50$0.15——
OrcaRouter$1.50$7.50$0.15——
Pioneer$1.50$7.50$0.15$1.50—
Prime Inference$1.50$7.50———
Requesty$1.50$7.00$0.15——
AI/ML API$1.95$9.75$0.20——
Kenari$0$0———
SAP AI Core—————

Jobs this model qualifies for

Comparisons