Gemini 2.5 Flash
by Google
Best price-performance model with hybrid reasoning capabilities for large-scale processing and agentic use cases. Offers well-rounded capabilities with thinking features optimized for low-latency, high-volume tasks requiring both speed and intelligence.
- Optimal price-performance ratio delivering well-rounded capabilities with hybrid reasoning
- Best for large-scale processing, low-latency applications, and high-volume agentic workflows
- Comprehensive multimodal support with native audio capabilities and Live API integration
- Enhanced thinking capabilities with configurable reasoning budgets for complex problem solving
- 1M token context window with superior speed and native tool use for real-time applications
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 3.1 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.
Gemini 3.5 FlashGoogle's most intelligent stable model for coding tasks in the Gemini 3 family. Gemini 3.5 Flash combines frontier-class intelligence with Flash-tier speed, making it ideal for complex coding workflows and agentic tasks at a cost-effective price.
Gemini 3 FlashGoogle's fastest frontier AI model built for speed at a fraction of the cost. Outperforms Gemini 2.5 Pro while being 3x faster. Excels at agentic coding (78% SWE-bench) and PhD-level reasoning (90.4% GPQA Diamond).