gemini-3.5-flash-lite

Gemini 3.5 Flash-Lite is the latest in our cost-effective Flash-Lite line of models. It's optimized for simple coding tasks, precise document understanding, and lightweight agentic workflows that require fast inference at minimal cost. 3.5 Flash-Lite is a suitable replacement model for Gemini 2.5 Flash and less complex Gemini 3 Flash workloads.

LiveGoogle1 protocol1M contextStream cancellation unsupported
Ngữ cảnh
1M
Input / 1M
$0.30
Output / 1M
$2.50
Loại dữ liệu
Protocol
1
  • generateContent

Status & performance

Last 7 days
Loading model performance

Capabilities

Văn bảnSuy luậnThị giácÂm thanhNgữ cảnh dàiBộ nhớ đệm

Bảng giá

Token đầu vào
$0.3/1M
Token đầu ra
$2.50/1M
Cached input
$0.03/1M
cached_output
$0.03/1M
Audio input
$0.3/1M
Audio output
$2.50/1M
Reasoning tokens
$2.50/1M
input_text
$0.3/1M
Hình ảnh
$0.3/1M
output_text
$2.50/1M
output_image
$2.50/1M
input_above_threshold
$0.3/1M
cached_input_above_threshold
$0.03/1M
output_above_threshold
$2.50/1M
input_image_above_threshold
$0.3/1M
input_audio_above_threshold
$0.3/1M

Prices in USD per 1M tokens unless noted otherwise. Batch calls and cache hits receive additional discounts; live rates apply in the Workspace.