Gemini 3.7 Flash

Gemini 3.7 Flash is Google's stable multimodal reasoning model for coding and agents. The official model ID is gemini-3.7-flash. Google documents a 1,048,576-token input limit, 65,536-token output limit, text, image, video, audio, and PDF input, plus function calling, structured outputs, code execution, file search, and search grounding. Introductory pricing is $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026.

Official sources: Gemini 3.7 Flash model page, Gemini models, and Google model pricing.

Gemini 3.7 Flash is Google’s latest Gemini 3 Flash model for natively multimodal reasoning, coding, and agentic workflows. Google’s model documentation lists the stable model ID as gemini-3.7-flash and says the model supports text, image, video, audio, and PDF inputs with text output.

• 1,048,576-token input limit for long specifications, documents, code context, and media-rich tasks
• 65,536-token output limit
• Native multimodal input across text, images, video, audio, and PDF
• Thinking controls at low, medium, and high effort
• Function calling and structured outputs for applications and agents
• Code execution, file search, URL context, and search grounding
• Google Maps grounding and Computer Use in preview
• Batch, Flex, and Priority inference support

Google’s current API documentation marks Gemini 3.7 Flash as stable with an August 2026 update. Google lists introductory pricing of $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026; verify the current pricing page before using those promotional rates in a production forecast.

Gemini 3.7 Flash is a practical candidate for multimodal applications, coding agents, document and media analysis, search-grounded workflows, and high-volume tasks that need a large context window without flagship-tier pricing. Test tool reliability, output quality, and the exact Google API route for your workload before committing to a long-running agent.