ModelPickr

Models / Google / Gemini 3.5 Flash Lite

Google · gemini-flash-lite

Gemini 3.5 Flash Lite

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

$0.30 in · $2.50 out

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

Provider input prices run from $0.15 to $0.38 per 1M tokens. Output prices run from $1.25 to $3.13.

Context
1,048,576
Max output
65,536
Cache read
$0.03
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
26

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$0.15$1.25$0.015$0.042—
302.AI$0.30$2.50———
Abacus$0.30$2.50$0.03——
AIHubMix$0.30$2.50$0.03——
CrossModel$0.30$2.50$0.03$0.30—
DevPass$0.30$2.50$0.03$0.083—
Eden AI$0.30$2.50$0.03$0.083—
Googlereference$0.30$2.50$0.03——
Impossibl$0.30$2.50$0.03——
LLM Gateway$0.30$2.50$0.03$0.083—
Merge Gateway$0.30$2.50$0.03——
NanoGPT$0.30$2.50$0.03$0.083—
Neon$0.30$2.50$0.03——
Ofox$0.30$2.50$0.03$0.083—
OpenCode$0.30$2.50$0.03——
OpenRouter$0.30$2.50$0.03$0.083—
Opper$0.30$2.50$0.03——
OrcaRouter$0.30$2.50$0.03——
Pioneer$0.30$2.50$0.03$0.30—
Requesty$0.30$2.50$0.03——
Tempr Gateway$0.30$2.50$0.03——
Vercel AI Gateway$0.30$2.50$0.03——
Vertex$0.30$2.50$0.03——
Cortecs$0.33$2.75$0.033$0.082—
Venice AI$0.38$3.13$0.038——
SAP AI Core—————

Jobs this model qualifies for