Gemini 3.6 Flash
Gemini 3.6 Flash is Google's token-efficient workhorse model: 17% fewer output tokens than 3.5 Flash, fewer reasoning steps and tool calls in multi-step agentic workflows, and higher-precision code edits with reduced execution loops. All input modalities (text/image/video/audio) unified at $1.50/1M; batch tier at 50% discount. Thinking model with configurable levels. Released July 21, 2026. 通过统一 API 即可完成接入,支持弹性并发、用量监控和团队级密钥管理,适合从快速验证到稳定调用的完整链路。
能力与模态
当前模型版本支持的输入输出能力
模型价格
价格与能力以接口实时数据为准
API 接口
当前模型可以使用的调用端点
API 接入示例
选择协议与语言,配置 API Key 后运行
先在环境变量中配置平台密钥 AI_GATEWAY_API_KEY · 适用于 Bash / zsh / WSL。
https://api.tikway.ai/v1beta/models/google/gemini-3.6-flash:generateContent1curl --fail-with-body 'https://api.tikway.ai/v1beta/models/google/gemini-3.6-flash:generateContent' \2 -H "x-goog-api-key: $AI_GATEWAY_API_KEY" \3 -H 'Content-Type: application/json' \4 -d '{5 "contents": [6 {7 "role": "user",8 "parts": [9 {10 "text": "用三句话介绍 Tikway"11 }12 ]13 }14 ]15}'