Skip to content
Gemini 3.6 Flash - Free Previous-Generation Multimodal Model, 1M Context

Gemini 3.6 Flash - Free Previous-Generation Multimodal Model, 1M Context

Model ID gemini-3.6-flash
This is a Gemini API free-tier model: no credit card required, but inputs and outputs are used by Google to improve its products, and rate limits are lower than on the paid tier.

Model Information

AttributeValue
Context length1,048,576 tokens
Max output65,536 tokens
Input price$0 (free tier)
Output price$0 (free tier)
ProviderGoogle DeepMind
StatusAvailable on the free tier
Input modalitiesText, image, video, audio, PDF
Release date2026-07

Description

Gemini 3.6 Flash is the previous generation of 3.8 Flash, and Google still positions it as a stable model suitable for production use. It performs evenly across code generation, agentic execution, and spatial reasoning, making it a good backup or comparison model for 3.8 Flash.

Like 3.8 Flash, it supports 1-million-token input, 65,536-token output, thinking levels, function calling, and structured output; the free tier likewise does not provide Batch or Context Caching.

Usage Example

curl https://generativelanguage.googleapis.com/v1beta/openai/chat/completions \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.6-flash",
    "messages": [{"role": "user", "content": "Summarize the key conclusions of this PDF"}]
  }'

Related Links

📚 Related Free Models

These models are also available for $0 on Gemini. Choose by context length and modality.

ModelContextDescription
Gemini 4 Hydrogen1MGemini 4 Hydrogen is Google’s free-tier flagship model
Gemini 3.5 Flash-Lite1MGoogle’s low-latency, high-throughput multimodal model
Gemini 3.8 Flash1MGoogle’s latest Flash multimodal model, built for

📋 View all Gemini free models →

🔗 Site Navigation

Last updated on · Source: Gemini official documentation and pricing pages. Quotas and prices may change at any time.