GeminiLimited-time

Gemini 3.7 Flash

Model ID:gemini-3.7-flash

gemini-3.7-flash

BalancedStreaming

Context window	1M
Input (CNY / Million Tokens)	¥1.2
Output (CNY / million tokens)	¥5
Cache read (CNY / million tokens)	¥0
Cache write (1h, yuan / million tokens)	¥6

Prices by channel

Channel	Input	Output	Read Cache	Cache hit	Cache Write (1h)	Cache write (5m)	Multiplier
default-2	¥1.2	¥5	¥0	¥0.8	¥6	—	1.00x
default-1	¥1.2	¥6	¥0	¥0.9	¥6	—	1.00x

Call example

Compatible with the Anthropic Messages native protocol; just fill in your API Key to get started.

Request examplecurl

curl https://<你的中转接口域名>/v1/messages \
  -H "x-api-key: sk-你的Key" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "gemini-3.7-flash",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "你好，请简单介绍一下自己" }
    ]
  }'

Back to examplesJSON

{
  "id": "msg_01abcDEF...",
  "type": "message",
  "role": "assistant",
  "model": "gemini-3.7-flash",
  "content": [
    { "type": "text", "text": "你好！我是 Gemini 3.7 Flash，很高兴为你服务。\n\n有什么可以帮你？" }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 303,
    "output_tokens": 73
  }
}

Tool Integration Tutorial

Use this model with your usual AI coding tool, billed per token.

How to Integrate Cline with API Gateways: VS Code Coding Agent Configuration

A tutorial on integrating the VS Code open-source coding agent Cline: how to create an sk- key, configure the API Provider and Base URL, and connect to Claude, GPT, or Gemini models.

Tutorial: Integrating Relay API in Cursor with Custom Base URL

Configure custom API Keys and Base URLs in Cursor's Settings → Models to use your own keys for accessing Claude, GPT, and Gemini models.

Continue Integration Guide: Custom Provider Setup for VS Code

A guide to integrating the Continue extension: add a custom Provider in config.yaml, configure the Base URL and sk- key to unify your usage of Claude, GPT, and Gemini.

View all model pricing Integration Documentation