Sync Gemini 3.5 Flash docs and pricing

docs/llmservice/models/gemini-3-5-flash.md

@@ -0,0 +1,39 @@
+# Gemini 3.5 Flash
+
+## Overview
+
+Gemini 3.5 Flash is a Flash-tier model in the Gemini 3 family. It is designed for low-latency, cost-efficient workloads that still require strong reasoning, coding support, and multimodal understanding.
+
+On B.AI, use the model ID `gemini-3.5-flash`.
+
+## Key Features
+
+* **Agentic Execution:** Suitable for sub-agent deployment, multi-step workflows, and rapid agentic loops at scale.
+* **Coding Support:** Optimized for iterative coding cycles, rapid exploration, and prototyping where fast turnaround matters.
+* **Configurable Thinking Levels:** Supports `minimal`, `low`, `medium`, and `high` thinking levels, with `medium` as the default.
+* **Combined Tool Use:** Supports function calling, code execution, Google Search grounding, URL context, and structured outputs.
+
+## Best Use Cases
+
+* **Agentic Workflows at Scale:** A strong fit for production agent systems that need fast, repeated tool calls and sustained task progress.
+* **Rapid Coding Iterations:** Useful for developer tools, code generation pipelines, debugging assistance, and interactive prototyping.
+* **Cost-Efficient Intelligence:** Suitable for high-volume production workloads that need a balance of speed, capability, and cost.
+
+## Capabilities and Limitations
+
+| Capability | Detailed Description |
+| :--- | :--- |
+| **Reasoning** | Strong reasoning with configurable thinking levels for balancing quality, latency, and cost. |
+| **Coding** | Optimized for iterative coding cycles and agentic coding workflows. |
+| **Multimodal** | Supports text, image, video, audio, and PDF input with text output. |
+| **Response Speed** | Flash-tier latency, including a `minimal` thinking level for faster chat-like responses. |
+| **Context Window** | Supports a context window of up to 1,048,576 tokens. |
+| **Max Output** | Supports up to 65,536 output tokens. |
+| **Tool Use** | Supports function calling, code execution, Google Search grounding, URL context, and structured outputs. |
+| **Multilingual** | Supports multilingual tasks across major languages. |
+
+## Credits Usage
+
+| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
+| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
+| **Gemini 3.5 Flash** | `1.50` | `1.50` | `0.15` | `9.00` | `14,000` | - |

docs/llmservice/pricing-and-usage.md

@@ -39,6 +39,7 @@ The platform uses a unified Credits system to measure and settle usage across al
 | Claude Sonnet 4.5 |                  3.00 |                        3.75 |                       0.30 |                  15.00 |                   10,000 |
 | Claude Haiku 4.5  |                  1.00 |                        1.25 |                       0.10 |                   5.00 |                   10,000 |
 | Gemini 3.1 Pro    |                  2.00 |                        2.00 |                       0.20 |                  12.00 |                   14,000 |
+| Gemini 3.5 Flash  |                  1.50 |                        1.50 |                       0.15 |                   9.00 |                   14,000 |
 | Gemini 3 Flash    |                  0.50 |                        0.50 |                       0.05 |                   3.00 |                   14,000 |
 
 ### Cache Pricing Notes
@@ -56,6 +57,10 @@ The platform supports two usage models: topping up Credits and subscription plan
 
 Top-up Credits are suitable for flexible, on-demand usage. Subscription plans are better suited for frequent users and include a fixed allowance within each billing period. When your subscription allowance is exhausted, the system will continue consuming Credits from your account balance.
 
+:::caution Free bonus Credits validity
+Free bonus Credits are valid for 30 days from the date they are issued, including Credits granted for new-user registration and Credits granted through top-up promotions. Any unused portion automatically expires after the validity period.
+:::
+
 ### Subscription Plans
 
 Two subscription plans are currently available:

i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-5-flash.md

@@ -0,0 +1,47 @@
+# Gemini 3.5 Flash
+
+## 概述
+
+Gemini 3.5 Flash 是 Gemini 3 系列中的 Flash 层级模型。它面向低延迟、高性价比的使用场景，同时保留较强的推理、编码和多模态理解能力。
+
+在 B.AI 中，请使用模型 ID：`gemini-3.5-flash`。
+
+---
+
+## 核心特性
+
+- **智能体执行：** 适合子智能体部署、多步骤工作流，以及大规模快速智能体循环
+- **编码支持：** 适用于迭代式编码、快速探索和原型开发等需要快速反馈的场景
+- **可配置思考等级：** 支持 `minimal`、`low`、`medium`、`high` 四个思考等级，默认等级为 `medium`
+- **组合工具调用：** 支持 function calling、code execution、Google Search grounding、URL context 和 structured outputs
+
+---
+
+## 适用场景
+
+- **大规模智能体工作流：** 适合需要持续推进任务、频繁调用工具的生产级智能体系统
+- **快速编码迭代：** 适合开发者工具、代码生成流水线、调试辅助和交互式原型开发
+- **高性价比智能能力：** 适合需要兼顾速度、能力和成本的高频生产工作负载
+
+---
+
+## 能力与限制
+
+| 能力 | 说明 |
+| :--- | :--- |
+| **推理能力** | 具备较强推理能力，可通过思考等级在质量、延迟和成本之间进行取舍 |
+| **编码能力** | 针对迭代式编码和智能体编码工作流进行优化 |
+| **多模态能力** | 支持文本、图像、视频、音频和 PDF 输入，输出为文本 |
+| **响应速度** | Flash 层级延迟，并支持 `minimal` 思考等级以获得更快的对话式响应 |
+| **上下文窗口** | 支持最高 1,048,576 tokens 的上下文窗口 |
+| **最大输出** | 支持最高 65,536 tokens 输出 |
+| **工具调用** | 支持 function calling、code execution、Google Search grounding、URL context 和 structured outputs |
+| **多语言能力** | 支持主要语言的多语言任务 |
+
+---
+
+## 积分消耗
+
+| 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
+| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
+| **Gemini 3.5 Flash** | `1.50` | `1.50` | `0.15` | `9.00` | `14,000` | - |

i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md

@@ -39,6 +39,7 @@
 | Claude Sonnet 4.5 | 3.00 | 3.75 | 0.30 | 15.00 | 10,000 |
 | Claude Haiku 4.5 | 1.00 | 1.25 | 0.10 | 5.00 | 10,000 |
 | Gemini 3.1 Pro | 2.00 | 2.00 | 0.20 | 12.00 | 14,000 |
+| Gemini 3.5 Flash | 1.50 | 1.50 | 0.15 | 9.00 | 14,000 |
 | Gemini 3 Flash | 0.50 | 0.50 | 0.05 | 3.00 | 14,000 |
 
 ### 缓存定价说明
@@ -56,6 +57,10 @@
 
 充值 Credits 适合灵活、按需使用。订阅套餐更适合高频用户，并会在每个计费周期内提供固定额度。当订阅额度耗尽后，系统会继续消耗你账户中的 Credits 余额。
 
+:::caution 免费赠送 Credits 有效期提醒
+平台免费赠送的 Credits（积分）自发放日起 30 天内有效，包括新用户注册赠送 Credits 和充值活动赠送 Credits。过期后未使用部分将自动失效。
+:::
+
 ### 订阅套餐
 
 当前提供两种订阅套餐：

i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js

@@ -235,6 +235,7 @@ const sidebars = {
             'llmservice/models/deepseek-v4-flash',
             'llmservice/models/gemini-3-1-pro',
             'llmservice/models/gemini-3-flash',
+            'llmservice/models/gemini-3-5-flash',
             'llmservice/models/glm-5-1',
             'llmservice/models/glm-5',
             'llmservice/models/kimi-k2.6',

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@x402-tron/docs",
-  "version": "1.2.20", 
+  "version": "1.2.21",
   "description": "x402-tron documentation",
   "license": "MIT",
   "scripts": {

sidebars.js

@@ -232,6 +232,7 @@ const sidebars = {
             'llmservice/models/deepseek-v4-flash',
             'llmservice/models/gemini-3-1-pro',
             'llmservice/models/gemini-3-flash',
+            'llmservice/models/gemini-3-5-flash',
             'llmservice/models/glm-5-1',
             'llmservice/models/glm-5',
             'llmservice/models/kimi-k2.6',