gemini-2.5-flash-lite API
About
Build advanced reasoning agents with gemini-2.5-flash-lite, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.09/1M input and $0.36/1M output tokens, native tool calling support. Access gemini-2.5-flash-lite via the Jiekou.AI API with up to 66K output tokens.
Capabilities
Input Modalities
textimagevideoaudio
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.09
Output
$0.36
Frequently Asked Questions
gemini-2.5-flash-lite by Jiekou.AI costs $0.09 per 1M input tokens and $0.36 per 1M output tokens.
Model Details
ID
gemini-2.5-flash-lite
Provider
Jiekou.AIFamily
gemini-flash-lite
Release Date
Jan 1, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
JIEKOU_API_KEY
API Base URL
https://api.jiekou.ai/openai