gemini-2.5-flash-lite
Googlegemini-2.5-flash-lite
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.
API Pricing
Price typeBilling expression
Official price
Base pricingPricing tier: base
- Input usage × $0.10
- Output usage × $0.40
- Cached read × $0.01
Gemini_Ultra×0.880% of official list price
Base pricingPricing tier: base
- Input usage × $0.08
- Output usage × $0.32
- Cached read × $0.0080
Group multiplier: x0.8
Official pricing is subject to the model provider's latest published pricing and may vary by request method or service region. Gemini_Ultra — TokenByte channel pricing. Actual prices and availability reflect current platform data.
Model information
Model providerGoogle
Model IDgemini-2.5-flash-lite
Context window1048576
InputTextImageVideoAudio
OutputText
Frequently asked questions
01What is Gemini 2.5 Flash Lite?
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e.
02How much does Gemini 2.5 Flash Lite cost?
Gemini 2.5 Flash Lite costs $0.10/M input tokens and $0.40/M output tokens, with separate rates for Cache Read at $0.01/M tokens, Cache Write at $0.08333/M tokens, Image Input at $0.10/M tokens, Input Audio at $0.30/M tokens, and Input Audio Cache at $0.03/M tokens.
03What is the context length of Gemini 2.5 Flash Lite?
Gemini 2.5 Flash Lite has a 1,048,576 token context window. It supports up to 65,535 completion tokens.