Gemini 2.5 Flash Lite
by Google
Most cost-efficient model in the 2.5 family released August 2025, optimized for high throughput and cost-sensitive deployments. Maintains 2.5-level quality while delivering superior performance compared to 2.0 Flash-Lite across all benchmarks.
- Most cost-efficient model in Gemini 2.5 family at $0.10 input, $0.40 output per 1M tokens
- Superior performance compared to 2.0 Flash-Lite across all key benchmarks with enhanced capabilities
- Speed optimized with lower latency than both 2.0 Flash-Lite and standard Flash models
- Controllable thinking capabilities available but disabled by default for maximum speed
- Enterprise-ready with full Google Search grounding and comprehensive tool integration support
Web Search
Search the web for current info.
Code Execution
Run Python code in a sandbox.
JSON Mode
Output responses in valid JSON format.
URL Context
Fetch and process content from URLs.
Google Maps
Ground responses in real-time Google Maps data for location-aware queries.
Image Generator
Generate images from text prompts.
Model Information
Supported Formats
Gemini 3.6 FlashGoogle's most intelligent stable model for coding tasks, released July 21, 2026 as the successor to Gemini 3.5 Flash. Combines frontier-class intelligence with Flash-tier speed, with full support for thinking, function calling, structured outputs, code execution, URL context, and search/Maps grounding.
Gemini 3.5 Flash LiteThe fastest and cheapest model in Google's 3.5 line, released July 21, 2026 as the successor to Gemini 3.1 Flash Lite. Built for high-volume, low-latency jobs like agentic search, document processing, and translation.
Gemini 3.1 ProGoogle's most advanced reasoning model (Gemini 3.1 Pro) with configurable thinking levels (minimal/low/medium/high) for optimal cost-performance balance. Successor to Gemini 3 Pro with enhanced reasoning and tool capabilities including Google Maps grounding.