Starstruk Logo MarkStarstruk

v0.1.150

Wei-Shaw/sub2apiv0.1.150Jul 10, 2026by github-actions[bot]

AI Summary

This release aligns GPT-5.6 billing with official pricing, adds support for cache write token billing, and introduces parallel_tool_calls compatibility mapping between Chat Completions and Responses APIs.

Key Highlights

  • GPT-5.6 cache write token independent pricing and usage statistics
  • parallel_tool_calls compatibility mapping between API formats
  • Codex client upgraded to version 0.144.1
  • Billing concurrency and recovery process improvements

New Features

  • GPT-5.6 cache write billing
  • parallel_tool_calls mapping
  • Codex client upgrade
  • Billing concurrency fixes

Full Release Notes

> AI API Gateway Platform - 将 AI 订阅配额分发和管理

- GPT-5.6 缓存写入计费：支持 cache write token 独立计价与用量统计
- parallel_tool_calls 兼容映射：Chat Completions 与 Responses API 互转时保留该字段（含显式 false）

- GPT-5.6 计费与官方定价对齐，显式配置的缓存写入价格优先生效
- 升级 Codex 客户端版本至 0.144.1，修复 gpt-5.6-luna 模型请求 404
- 加固计费并发与支付恢复流程，防止并发场景下的余额与订阅状态异常

- 修复 remote compact 失败与重复计费：保留 SSE 事件流中的 compaction 输出项，上游等待期间向下游发送心跳，避免反向代理空闲超时断连（#3887）
- 修复 GPT-5.6 max 推理强度不被识别的问题；effort 提取改用模型候选列表，带后缀模型的用量元数据不再丢失
- 修复管理端用户用量明细 request_type 筛选不生效的问题
- 修复 Windows 环境下 WebSocket 连接重置未被正确识别的问题
- 补齐英文语言包缺失的翻译条目



---

## 📥 Installation

**Docker:**
```bash
# Docker Hub
docker pull weishaw/sub2api:0.1.150

# GitHub Container Registry
docker pull ghcr.io/wei-shaw/sub2api:0.1.150
```

**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)