v0.2.16
Wei-Shaw/sub2apiv0.2.16Oct 13, 2026by github-actions[bot]
Upgrading?
AI Summary
This release introduces Claude Haiku 5.5 model support and Gemini explicit context caching, alongside enhanced Vertex integration. It includes numerous bug fixes to improve stability across various AI providers and user interface improvements.
Key Highlights
- Added Claude Haiku 5.5 model support with full integration for registration, pricing, and billing.
- Implemented Gemini explicit context caching with support for creation, renewal, and deletion.
- Expanded Gemini support to include Vertex (Agent Platform) with API Key authentication.
- Enhanced temporary un-schedulable rules with scope options to pause accounts or cool specific models.
- Optimized GPT-6.1 Sol with no long-context fees and a default context size of 500k.
New Features
- Claude Haiku 5.5 model adaptation and Responses bridge integration.
- Gemini explicit context caching with Pro/Flash series storage pricing.
- Gemini Vertex (Agent Platform) support including service account sync and model details.
- Gemini AI Studio AQ. format Key adaptation.
- Temporary un-schedulable rules with scope options (account vs. model cooling).
- Multi-language support for group names and descriptions.
- New Account Name column in operations request details.
- Kimi International Coding endpoint (api.kimi.ai) quota query support.
Full Release Notes
> AI API Gateway Platform - 将 AI 订阅配额分发和管理 Gemini 支持显式上下文缓存(AI Studio / Vertex / 自建网关上游),并新增 Claude Haiku 5.5 模型适配。 ## 新增功能 - Claude Haiku 5.5:全链路适配模型注册、推理强度、定价与计费,并接入 Responses 桥接 - Gemini 显式上下文缓存:支持创建、续期、删除缓存,内置官方存储价并按 Pro / Flash 系列兜底,存储费按 API Key 额度与订阅额度预留校验 - Gemini Vertex(Agent Platform):支持 API Key 认证,服务账号支持同步上游模型列表,模型列表与详情接口支持 Vertex 账号 - Gemini AI Studio:适配新的 AQ. 格式 Key - 临时不可调度规则新增作用范围选项:可选择命中后暂停整个账号或只冷却当前模型,未设置的存量规则行为不变 - 分组名称与描述支持多语言 - 运维请求详情表新增账号名称列 ## 优化改进 - GPT-6.1 Sol 订阅账号不再收取长上下文附加费 - GPT-6.1 Sol 生成上下文默认值提升至 500k - Gemini 3.6 Flash 兜底价改为官方优惠价 - 第三方上游 API Key 与 Vertex 账号不再套用 AI Studio 等级和模拟配额 - Vertex 显示名改为 Agent Platform (Vertex) - Kimi 国际版 Coding 端点(api.kimi.ai)支持配额查询 ## Bug 修复 - 修复上游拒绝结构化输入时 Chat 回退重试的问题,并保留 Responses 语义、避免不安全重试 - 修复 Kimi / DeepSeek / MiniMax 等非 OpenAI 账号被注入 Codex 图像生成桥接导致 400 的问题 - 修复 Gemini 引用不存在的缓存返回 403 时账号被停用并换号的问题 - 修复 Gemini 工具结果中的图片丢失问题 - 修复 Antigravity 图像模型限流影响同账号其他模型的问题 - 修复显式模型级 401 规则在故障转移、计数、Bedrock 等入口未生效、仍整号置错的问题 - 修复 Gemini 原生路由网关本地错误在运维中的归类问题 - 修复 Gemini 授权链接生成失败时错误信息丢失的问题 - 修复同步上游模型失败时未显示后端错误原因的问题 - 修复风控审核范围中残留已删除分组的问题 - 修复分组 RPM 覆盖加载过期数据的问题,并拒绝非正数的倍率修改 - 修复支付二维码倒计时漂移、用量倒计时切回标签页不刷新的问题 - 修复渠道监控 v2 设置无法添加缺失平台、自动刷新不更新缓存可用性的问题 - 修复运维自定义时间范围未按本地时区初始化的问题 - 修复下拉选择框在输入法组字时键盘输入被打断的问题 - 修复账号列表中分组名称显示不全的问题 --- ## 📥 Installation **Docker:** ```bash # Docker Hub docker pull weishaw/sub2api:0.2.16 # GitHub Container Registry docker pull ghcr.io/wei-shaw/sub2api:0.2.16 ``` **One-line install (Linux):** ```bash curl -sSL https://raw.githubusercontent.com/Wei-Shaw/sub2api/main/deploy/install.sh | sudo bash ``` **Manual download:** Download the appropriate archive for your platform from the assets below. ## 📚 Documentation - [GitHub Repository](https://github.com/Wei-Shaw/sub2api) - [Installation Guide](https://github.com/Wei-Shaw/sub2api/blob/main/deploy/README.md)
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.
:cherry_blossom: A command-line fuzzy finder