New APINew API
使用指南部署安装API 参考AI 应用Skills插件帮助支持商务合作合规与使用政策
⚠️合规提示:本项目仅用于合法授权的 API 网关、内部管理和私有化部署场景。请遵守上游服务条款、平台规则、监管要求和内容安全要求。

更新日志

版本日志信息 · 数据更新于 2026-11-17 23:29:21

如需查看全部历史版本,请访问 GitHub Releases 页面,本页面从该页面定时获取最新更新信息。

v1.0.0-rc.51

最新正式版本 · 发布于 2026-11-13 17:30:24 (中国时间)

[!IMPORTANT] 修复 v1.0.0-rc.50 在有 AES-NI、没有 AVX 的 x86-64 CPU 上崩溃并反复重启的问题(#8314)。Celeron、Pentium、Atom 一类 CPU(如 J4125)和只提供 AES、不提供 AVX 的虚拟机会受影响:处理聊天等请求时进程因 SIGILL 退出,模型列表和管理后台仍能打开,看起来像间歇性的 502。在这类机器上运行 rc.50 的请升级到本版本。

本版本包含 rc.50 新增的提供商插件、请求处理插件和社区插件市场。提供商插件把一个上游厂商接成一种渠道;请求处理插件在请求和回复上运行,可以按全局、分组、渠道和模型生效。从 rc.49 或更早版本升级时请注意下面几点。

原敏感词设置在首次启动时迁成一个「请求过滤」实例,旧设置项会被删除。命中时返回 400 request_rejected,原来是 500 sensitive_words_detected。回滚到旧版本后敏感词检查是关闭的,需要重新填写。

多节点部署:设置、权限、插件、渠道等手动改动几秒内同步到所有节点。CHANNEL_UPDATE_FREQUENCY 的定时余额更新改为只在主节点运行。超过 30 天的已结束系统任务会被自动删除,需要保留更久的请先在 系统设置 → 运维 → 日志维护 里改保留天数。

Vertex AI 插件 1.3.1 起,视频请求发到渠道填的部署地区,不再固定发到 global。升级前请确认所用的视频模型在该地区可用。

Fixes v1.0.0-rc.50 crashing and restarting over and over on x86-64 CPUs that have AES-NI but not AVX (#8314). Celeron, Pentium and Atom parts (such as the J4125) and virtual machines that offer AES but not AVX are affected: the process exits with SIGILL while handling chat and similar requests, while the model list and the admin console still open, so it looks like an intermittent 502. If you run rc.50 on such a machine, upgrade to this release.

This release includes the provider plugins, request processing plugins and community plugin marketplace added in rc.50. A provider plugin turns an upstream vendor into a channel type. A request processing plugin runs on requests and replies, scoped globally or to groups, channels and models. When upgrading from rc.49 or earlier, note the following.

On first start, the old sensitive word setting becomes a Request filter instance and the old setting is removed. A match now returns 400 request_rejected instead of 500 sensitive_words_detected. After rolling back to an older version, sensitive word checks are off until you fill them in again.

Multi-node deployments: manual changes to settings, permissions, plugins, channels and more reach every node within seconds. Scheduled balance updates from CHANNEL_UPDATE_FREQUENCY now run on the master node only. Finished system tasks older than 30 days are deleted automatically. To keep them longer, change the retention days in System Settings → Operations → Log Maintenance first.

From Vertex AI plugin 1.3.1, video requests go to the channel's deployment region instead of always to global. Before upgrading, check that the video models you use are available in that region.

中文

  • 修复:修复了 rc.50 在有 AES-NI、没有 AVX 的 x86-64 CPU 上处理请求时崩溃的问题(#8314)。JSON 库 MoeForge moego 升级到 v0.1.0-alpha.3,这类 CPU 改用 SSE 编码的 AES 指令,结果与其他 CPU 相同。
  • 插件:提供商插件可以接入路由、协议转换、模型列表、需要登录的上游(登录与令牌刷新)、余额查询和定时维护。请求处理插件可以试运行,每处修改记入使用日志;内置请求过滤、请求脱敏、全局参数覆盖、自动推理强度、图片压缩和内容审核。插件市场新增社区来源,官方和社区插件都能按 8 位插件码安装,安装时显示使用说明和更新日志;插件下载站点可以选主站或备用站。
  • 多节点:设置、权限、插件、登录方式、模型、订阅套餐和渠道的手动改动在各节点几秒内生效,系统信息页能看到同步进度和加载失败的节点。系统任务记录每天自动清理,默认保留 30 天。「更新全部余额」改为后台任务,列表随进度刷新。
  • 计费:图片张数按最终发给上游的请求计算,包括 SiliconFlow 的 batch_size、Imagen 的 sampleCount(不填按 4 张)和 Replicate 的 num_outputs。插件或渠道覆盖改了张数,预扣也跟着变。
  • 支付:易支付的签名方式可以选 MD5 或 RSA。
  • 其他:注册、修改密码、初始化向导和管理员编辑用户时会显示密码强度、长度要求和加强建议,只有长度不符合要求时才不能提交。新增 HOST 环境变量设置监听地址。DeepSeek 渠道的 Chat Completions 请求会把 developer 角色转成 system。修复了透传请求重试时,新渠道可能收到残缺请求体的问题。修复了切换渠道后,模型重定向同步把上一个渠道的模型名加进当前渠道的问题。修复了用输入法输入风险确认文字后按钮仍不可用的问题。修复了渠道插件设置里过长的内容把设置区撑出渠道编辑抽屉的问题。登录页的协议同意文字现在会翻译。插件运行时升级到 MoeForge moejs v0.1.0。

English

  • Fix: Fixed the problem of rc.50 crashing while handling requests on x86-64 CPUs that have AES-NI but not AVX (#8314). The JSON library MoeForge moego is now v0.1.0-alpha.3, which uses the SSE encodings of the AES instructions on such CPUs, with the same results as on other CPUs.
  • Plugins: Provider plugins can bring routes, protocol conversion, model lists, upstreams that need sign-in (login and token refresh), balance queries and scheduled maintenance. Request processing plugins can be dry-run, and every change they make is recorded in the usage log. Built-in ones cover request filtering, request redaction, global parameter overrides, automatic reasoning effort, image compression and content moderation. The marketplace adds a community source. Official and community plugins can be installed by their 8-digit plugin code, and the install dialog shows the usage guide and changelog. Administrators choose the main or backup download site.
  • Multi-node: Manual changes to settings, permissions, plugins, login methods, models, subscription plans and channels take effect on every node within seconds. The system info page shows sync progress and nodes that failed to load a change. System task records are cleaned up daily and kept for 30 days by default. Update All Balances runs as a background task, and the list refreshes as it progresses.
  • Billing: Image counts come from the final request sent upstream, including SiliconFlow batch_size, Imagen sampleCount (4 when omitted) and Replicate num_outputs. When a plugin or channel override changes the count, the pre-charge follows it.
  • Payment: Epay can sign with MD5 or RSA, chosen in its Signature type setting.
  • Also: Sign-up, password change, the setup wizard and the admin user editor show password strength, the length requirement and tips for a stronger password. Only the length blocks submission. Added the HOST environment variable to set the listen address. DeepSeek channels map the developer role to system in Chat Completions requests. Fixed the problem of a retried pass-through request sending an incomplete body to the next channel. Fixed the problem of model redirect sync adding the previous channel's model names after switching channels. Fixed the problem of the risk confirmation button staying disabled after typing the confirmation text with an input method. Fixed the problem of long content in a channel's plugin settings pushing the settings out of the channel drawer. The legal consent text on sign-in pages is now translated. The plugin runtime is now MoeForge moejs v0.1.0.

What's Changed

rc.50 的变更列表 / rc.50 change list: https://github.com/QuantumNous/new-api/releases/tag/v1.0.0-rc.50

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.50...v1.0.0-rc.51

下载资源


v1.0.0-rc.50

正式版本 · 发布于 2026-11-12 22:15:24 (中国时间)

[!IMPORTANT] 新增提供商插件、请求处理插件和社区插件市场。提供商插件把一个上游厂商接成一种渠道;请求处理插件在请求和回复上运行,可以按全局、分组、渠道和模型生效。

原敏感词设置在首次启动时迁成一个「请求过滤」实例,旧设置项会被删除。命中时返回 400 request_rejected,原来是 500 sensitive_words_detected。回滚到旧版本后敏感词检查是关闭的,需要重新填写。

多节点部署:设置、权限、插件、渠道等手动改动几秒内同步到所有节点。CHANNEL_UPDATE_FREQUENCY 的定时余额更新改为只在主节点运行。超过 30 天的已结束系统任务会被自动删除,需要保留更久的请先在 系统设置 → 运维 → 日志维护 里改保留天数。

Vertex AI 插件 1.3.1 起,视频请求发到渠道填的部署地区,不再固定发到 global。升级前请确认所用的视频模型在该地区可用。

Added provider plugins, request processing plugins and a community plugin marketplace. A provider plugin turns an upstream vendor into a channel type. A request processing plugin runs on requests and replies, scoped globally or to groups, channels and models.

On first start, the old sensitive word setting becomes a Request filter instance and the old setting is removed. A match now returns 400 request_rejected instead of 500 sensitive_words_detected. After rolling back to an older version, sensitive word checks are off until you fill them in again.

Multi-node deployments: manual changes to settings, permissions, plugins, channels and more reach every node within seconds. Scheduled balance updates from CHANNEL_UPDATE_FREQUENCY now run on the master node only. Finished system tasks older than 30 days are deleted automatically. To keep them longer, change the retention days in System Settings → Operations → Log Maintenance first.

From Vertex AI plugin 1.3.1, video requests go to the channel's deployment region instead of always to global. Before upgrading, check that the video models you use are available in that region.

中文

  • 插件:提供商插件可以接入路由、协议转换、模型列表、需要登录的上游(登录与令牌刷新)、余额查询和定时维护。请求处理插件可以试运行,每处修改记入使用日志;内置请求过滤、请求脱敏、全局参数覆盖、自动推理强度、图片压缩和内容审核。插件市场新增社区来源,官方和社区插件都能按 8 位插件码安装,安装时显示使用说明和更新日志;插件下载站点可以选主站或备用站。
  • 多节点:设置、权限、插件、登录方式、模型、订阅套餐和渠道的手动改动在各节点几秒内生效,系统信息页能看到同步进度和加载失败的节点。系统任务记录每天自动清理,默认保留 30 天。「更新全部余额」改为后台任务,列表随进度刷新。
  • 计费:图片张数按最终发给上游的请求计算,包括 SiliconFlow 的 batch_size、Imagen 的 sampleCount(不填按 4 张)和 Replicate 的 num_outputs。插件或渠道覆盖改了张数,预扣也跟着变。
  • 支付:易支付的签名方式可以选 MD5 或 RSA。
  • 其他:新增 HOST 环境变量设置监听地址。DeepSeek 渠道的 Chat Completions 请求会把 developer 角色转成 system。修复了透传请求重试时,新渠道可能收到残缺请求体的问题。修复了切换渠道后,模型重定向同步把上一个渠道的模型名加进当前渠道的问题。修复了用输入法输入风险确认文字后按钮仍不可用的问题。登录页的协议同意文字现在会翻译。插件运行时升级到 MoeForge moejs v0.1.0。

English

  • Plugins: Provider plugins can bring routes, protocol conversion, model lists, upstreams that need sign-in (login and token refresh), balance queries and scheduled maintenance. Request processing plugins can be dry-run, and every change they make is recorded in the usage log. Built-in ones cover request filtering, request redaction, global parameter overrides, automatic reasoning effort, image compression and content moderation. The marketplace adds a community source. Official and community plugins can be installed by their 8-digit plugin code, and the install dialog shows the usage guide and changelog. Administrators choose the main or backup download site.
  • Multi-node: Manual changes to settings, permissions, plugins, login methods, models, subscription plans and channels take effect on every node within seconds. The system info page shows sync progress and nodes that failed to load a change. System task records are cleaned up daily and kept for 30 days by default. Update All Balances runs as a background task, and the list refreshes as it progresses.
  • Billing: Image counts come from the final request sent upstream, including SiliconFlow batch_size, Imagen sampleCount (4 when omitted) and Replicate num_outputs. When a plugin or channel override changes the count, the pre-charge follows it.
  • Payment: Epay can sign with MD5 or RSA, chosen in its Signature type setting.
  • Also: Added the HOST environment variable to set the listen address. DeepSeek channels map the developer role to system in Chat Completions requests. Fixed the problem of a retried pass-through request sending an incomplete body to the next channel. Fixed the problem of model redirect sync adding the previous channel's model names after switching channels. Fixed the problem of the risk confirmation button staying disabled after typing the confirmation text with an input method. The legal consent text on sign-in pages is now translated. The plugin runtime is now MoeForge moejs v0.1.0.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.49...v1.0.0-rc.50

下载资源


v1.0.0-rc.49

正式版本 · 发布于 2026-11-08 13:06:38 (中国时间)

[!IMPORTANT] 增加了 gpt-image-2.6 的支持。它的新参数 complexity、svg、frame_count、frame_duration_ms 和 markup 会转发给上游,可以生成 SVG 和 GIF,编辑图片时可以带 markup 标注图层。

修复了 Redis 集群和分片 Redis 上修改用户或令牌时报 keys must in same slot 的问题。多节点部署请把所有节点一起升级,新旧版本混跑时,一个节点上的用户和令牌变更不一定能及时同步到另一个版本的节点。

SQLITE_PATH 只写文件路径时,现在和默认配置一样开启 WAL 和写入等待。数据库旁边会多出 -wal 和 -shm 文件,备份时要一起复制。

模型定价保存时会逐个模型列出当前价格和新价格,确认后才保存。删掉的价格在保存前可以撤销。

Added support for gpt-image-2.6. Its new parameters complexity, svg, frame_count, frame_duration_ms, and markup are forwarded to the upstream, so it can generate SVG and GIF images, and image edits can include a markup layer.

Fixed the problem of keys must in same slot errors when editing users or tokens on Redis Cluster or sharded Redis. Upgrade every node of a multi-node deployment together. While old and new versions run side by side, a user or token change on one node may not reach nodes on the other version in time.

A SQLITE_PATH that is only a file path now gets WAL and the busy timeout, the same as the default setting. -wal and -shm files appear next to the database. Copy them together with it when you back up.

Saving Model Pricing now lists the current and new price of each model and saves only after you confirm. A deleted price can be undone until you save.

中文

  • 任务插件:增加了 Vertex AI 渠道的 Gemini Omni 1.2 Flash,视频最长 15 秒。修复了 Gemini Omni 只把第一张输入图片发给 Vertex 的问题。Gemini Omni 生成失败时会返回失败原因。从插件市场安装或上传的插件也能用顶层的 /v1 地址调用了,比如 TypeSafe 的 POST /v1/systemone。
  • 计费:模型定价会列出价格需要处理的模型,选中模型能看到原因和处理方法。只统计启用的渠道实际提供的模型,内置价格只在已保存或有渠道提供时才列出。删掉的价格在保存前只是草稿,可以撤销。改过的行会显示新旧价格,保存时逐个模型列出当前价格和新价格,确认后才保存。在手机上,标签页单独占一行可以滑动,次要操作收进了菜单。
  • 渠道:增加了 gpt-image-2.6 的支持,complexity、svg、frame_count、frame_duration_ms 和 markup 参数会转发给上游,可以生成 SVG 和 GIF,编辑图片时可以带 markup 标注图层。DeepSeek 官方 Responses 接口的工具调用历史缺少 reasoning 时会自动补上,避免 DeepSeek 因此返回 400。高级自定义渠道的入口路径增加了 /v1/tools/search 和 /v1/tools/fetch。修复了 Vertex AI 服务账号每个请求都重新换取访问令牌的问题,令牌现在缓存到过期前 5 分钟。修复了多密钥渠道的密钥全部失败后,重新启用其中一个密钥,渠道仍然处于自动禁用的问题。修复了手动禁用的渠道在请求失败后变成自动禁用、又被自动测试重新启用的问题。渠道亲和性里的会话规则可以单独清空自己的缓存,刷新统计和清空缓存的说明也写清楚了。
  • 其他:修复了 Redis 集群和分片 Redis 上修改用户或令牌时报错的问题。修复了 SQLITE_PATH 只写文件路径时丢掉 WAL 和写入等待设置,并发写入报 "database is locked" 的问题。修复了用邀请码通过 OAuth 注册的新用户没有记录邀请人的问题。

English

  • Task plugins: Added Gemini Omni 1.2 Flash on Vertex AI channels, with videos up to 15 seconds. Fixed the problem of Gemini Omni sending only the first input image to Vertex. A failed Gemini Omni generation now returns the reason. Plugins installed from the marketplace or uploaded can now be called at their top-level /v1 paths too, such as TypeSafe's POST /v1/systemone.
  • Billing: Model Pricing lists the models whose prices need attention. Select a model to see the reason and what to change. Only models an enabled channel serves are counted, and built-in prices are listed only when saved or served by a channel. A deleted price stays a draft until you save, and you can undo it. Changed rows show the old and new prices. Every save lists the current and new price of each model and saves only after you confirm. On phones, the tabs have their own scrollable row and secondary actions are in a menu.
  • Channels: Added support for gpt-image-2.6. Its complexity, svg, frame_count, frame_duration_ms, and markup parameters are forwarded to the upstream, so it can generate SVG and GIF images, and image edits can include a markup layer. When tool call history sent to DeepSeek's official Responses API lacks reasoning, it is filled in, so DeepSeek does not reject the request with a 400. Advanced Custom channels can use the incoming paths /v1/tools/search and /v1/tools/fetch. Fixed the problem of Vertex AI service accounts requesting a new access token for every request. Tokens are now cached until 5 minutes before they expire. Fixed the problem of a multi-key channel staying auto-disabled when one key was enabled again after all keys failed. Fixed the problem of a manually disabled channel becoming auto-disabled after a failed request, which let automatic tests enable it again. Session rules in Channel Affinity can clear their own cache, and the refresh and clear actions are explained more clearly.
  • Also: Fixed the problem of errors when editing users or tokens on Redis Cluster or sharded Redis. Fixed the problem of a SQLITE_PATH with only a file path dropping the WAL and busy timeout settings, which made concurrent writes fail with "database is locked". Fixed the problem of new OAuth users who signed up with an invite code not recording the inviter.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.48...v1.0.0-rc.49

下载资源


v1.0.0-rc.48

正式版本 · 发布于 2026-11-04 23:40:15 (中国时间)

[!IMPORTANT] Redis 里的用户、令牌和会话缓存加了签名。多节点部署请把所有节点一起升级,新节点遇到旧版本写的缓存会回数据库重新读取。

任务插件可以用厂商自己的接口地址调用了,原来带前缀的地址照常可用。原生请求按客户端写的原样发给厂商。可灵、Vidu、MiniMax 和火山方舟的请求带 callback_url 时会被拒绝。

增加了任务模型的价格提醒。插件改动后没法计费的模型,会在模型定价里标成「价格待处理」。

User, token, and session caches in Redis are now signed. Upgrade every node of a multi-node deployment together. A new node reads from the database again when it finds a cache written by an older version.

Task plugins can now be called at the vendors' own API paths. The prefixed paths still work. Native requests go to the vendor exactly as the client wrote them. Kling, Vidu, MiniMax, and Volcengine Ark requests with callback_url are rejected.

Added price reminders for task models. Models a plugin can no longer charge are marked "Price needs attention" in Model Pricing.

中文

  • 安全:Redis 里的用户、令牌和会话缓存加了签名,被改过、没有签名或已经过期的缓存会回数据库重新读取。修复了两步验证锁定结束后,再错一次就又被锁定的问题。
  • 任务插件:增加了用厂商官方接口地址调用任务插件的功能,比如可灵的 /v1/videos/text2video、Vidu 的 /ent/v2/text2video,回复保持厂商的格式和错误码。即梦改用官方的 Bearer 接口。增加了可灵 4.0,时长 3 到 30 秒,按可灵返回的金额扣费。用 /v1/videos 调可灵时,尺寸按宽高比选最接近的官方比例。增加了 Vertex AI 渠道的 Gemini Omni 视频生成,按 Vertex 报告的 token 计费,需要服务账号 JSON 密钥。
  • 计费:增加了任务模型的价格提醒。没设价格、价格用到插件不再提供的用量、插件不再提供的模型,会在模型定价里标成「价格待处理」并写明原因,可以按「价格状态」筛选。上传、安装或启用插件时也会列出这些模型,超级管理员的侧边栏会显示数量。修复了 prompt_tokens_details 里的 cache_creation_input_tokens 没有计费的问题。Gemini 向量改按上游返回的用量计费。修复了表达式里的按次计费在模型广场显示成按量计费的问题。
  • 渠道:增加了 Vertex AI 渠道切换到 v1beta1 接口的开关。增加了 Azure 渠道开启 Responses WebSocket 的功能。增加了 gemini-4-argon 的思考强度支持。gpt-6.1-sol 和 gpt-6.1-terra 按 GPT-6 的规则发参数。增加了上游 HTTP/2 连接的健康检查,设置 RELAY_HTTP2_PING_IDLE_TIMEOUT 开启,默认关闭。创建渠道的接口会返回新渠道的 ID,批量创建时每一行对应一个 ID。修复了渠道亲和的重试没有从最高优先级开始的问题。
  • 转换:修复了单独一行 [DONE] 没被当成流结束的问题。修复了 stop 数组里混有非字符串时转成 Claude 出错的问题。修复了转成 Claude 时工具参数里的大整数被改掉的问题。修复了 Gemini 同时返回文字和工具调用时丢掉文字的问题。修复了 Bedrock Invoke 丢掉 safeguards 的问题。修复了 Cloudflare 向量回复缺少 data 的问题。修复了 xAI 流式用量丢掉 token 明细的问题。改写请求时只改需要改的字段,其余部分保持客户端原样,字段顺序和数字不再变。
  • 其他:修复了退出登录后连着弹出几个「会话已过期」的问题。修复了 Turnstile 密钥和开关一起保存时报错的问题。修复了个人资料页还能设置管理员已经关掉的侧边栏项目的问题。修复了日志轮转后访问日志和崩溃日志还写进旧文件的问题。模型性能统计会算上客户端提前断开的非流式成功请求,以及插件立即完成的任务。

English

  • Security: User, token, and session caches in Redis are now signed. A cache that was changed, has no signature, or has expired is read again from the database. Fixed the problem of one more wrong 2FA code after a lockout ended locking the account again.
  • Task plugins: Added calling task plugins at the vendors' official API paths, such as Kling's /v1/videos/text2video and Vidu's /ent/v2/text2video. Replies keep the vendor's format and error codes. Jimeng now uses the official Bearer API. Added Kling 4.0, with durations of 3 to 30 seconds, charged at the amount Kling returns. When Kling is called through /v1/videos, the size maps to the closest official aspect ratio. Added Gemini Omni video generation on Vertex AI channels, billed by the tokens Vertex reports. It needs a service account JSON key.
  • Billing: Added price reminders for task models. A model with no price, a price that uses usage the plugin no longer provides, or a model the plugin no longer offers is marked "Price needs attention" in Model Pricing with the reason, and a "Price status" filter lists them. Uploading, installing, or enabling a plugin lists these models too, and the sidebar shows the count to super administrators. Fixed the problem of cache_creation_input_tokens in prompt_tokens_details going unbilled. Gemini embeddings are billed by the usage the upstream returns. Fixed the problem of per-request expression prices showing as usage-based in the Model Square.
  • Channels: Added a switch that sends a Vertex AI channel's requests to v1beta1. Added Responses WebSocket for Azure channels. Added thinking effort support for gemini-4-argon. gpt-6.1-sol and gpt-6.1-terra now follow the GPT-6 parameter rules. Added a health check for upstream HTTP/2 connections, off by default; set RELAY_HTTP2_PING_IDLE_TIMEOUT to turn it on. Creating channels returns the new channel IDs, one for each input line in a batch. Fixed the problem of a channel affinity retry not starting from the highest priority.
  • Conversion: Fixed the problem of a bare [DONE] line not ending the stream. Fixed the problem of a stop array with non-string items failing on the way to Claude. Fixed the problem of large integers in tool arguments changing on the way to Claude. Fixed the problem of Gemini text being dropped when it came with tool calls. Fixed the problem of Bedrock Invoke dropping safeguards. Fixed the problem of Cloudflare embedding replies missing data. Fixed the problem of xAI stream usage losing its token details. Request rewrites change only the fields they need, so the rest keeps the client's field order and numbers.
  • Also: Fixed the problem of several "session expired" messages popping up after sign-out. Fixed the problem of an error when saving Turnstile keys and turning it on together. Fixed the problem of the profile page offering sidebar items the administrator turned off. Fixed the problem of access and crash logs still going to the old file after log rotation. Model performance metrics now count successful non-stream requests whose client disconnected early, and tasks a plugin finishes at once.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.47...v1.0.0-rc.48

下载资源


v1.0.0-rc.47

正式版本 · 发布于 2026-10-25 17:04:29 (中国时间)

[!IMPORTANT] 增加了普通渠道和任务插件一起选择渠道的功能。同一个模型名,插件和普通渠道都有的时候,以前请求都发给插件,现在按优先级和权重选择渠道。

这个模型的定价如果还是按任务插件写的,普通渠道会报价格错误,不会扣额度。可以单独给普通渠道设置价格。

增加了 OpenAI 12 小时提示缓存单独计价的功能,按输入价格的 2.5 倍收费。

修复了视频任务超过 24 小时就被退款的问题。默认等到 72 小时才退款。

Added selecting a channel from both a regular channel and a task plugin. On image, video, and Responses endpoints, a model both can serve used to send every request to the plugin. The channel is now selected by priority and weight.

If that model's price is still written for the task plugin, a regular channel returns a price error and does not charge. Set a regular price for it in pricing.

Added a separate price for OpenAI's 12-hour prompt cache, at 2.5 times the input price. It was charged at the 30-minute rate.

Fixed the problem of video tasks being refunded after 24 hours. They now wait 72 hours. If you set TASK_TIMEOUT_MINUTES yourself, that time stays.

中文

  • 渠道:增加了图片、视频和 Responses 上,普通渠道和任务插件按优先级和权重一起选择渠道的功能。原生插件地址继续走对应的插件。普通渠道和插件各用各的价格。
  • 计费:增加了 OpenAI 12 小时提示缓存单独计价的功能,按输入价格的 2.5 倍收费。gpt-6-astra 的 12 小时写入是每百万 token 25 美元,超过 272K token 是 50 美元。修复了 Claude 缓存写入没拆成 5 分钟和 1 小时时不计费的问题,没拆开的按 5 分钟计费。
  • 价格同步:增加了按站点汇率调整上游价格的功能。可以保持来源价格,也可以乘以或除以汇率。价格相同的模型也能选出来一起改。
  • 任务:修复了视频任务超过 24 小时就被退款的问题,默认等到 72 小时。自己设过 TASK_TIMEOUT_MINUTES 的,还是用你设的数。修复了可灵按 metadata 里的时长生成、计费却按外面的时长算的问题。增加了任务插件原生接口接收文件上传的功能。任务插件可以读到客户端请求头,Authorization 和 Cookie 不会给插件。
  • 流式:修复了大段内容传得慢就被当成断开的问题。修复了 Responses 已经回复完、日志里却记成断开的问题,用量照常记。
  • 其他:修复了结构化输出和工具参数字段顺序被打乱的问题,按客户端原来的顺序发给上游。修复了 Chat 转 Gemini 时丢掉 imageConfig 的问题,图片尺寸和比例会带过去。修复了高级自定义保存后「透传请求体」丢失的问题。修复了编辑令牌或模型时,切到另一条还留着上一条内容的问题。修复了访问日志记下网址里的密钥的问题。增加了使用日志详情里复制模型名的功能。

English

  • Channels: Added selecting a channel by priority and weight between a regular channel and a task plugin, on image, video, and Responses endpoints. A plugin's own address still goes to that plugin. Regular channels and plugins keep separate prices.
  • Billing: Added a separate price for OpenAI's 12-hour prompt cache, at 2.5 times the input price. gpt-6-astra bills 12-hour writes at $25 per million tokens, and $50 above 272K tokens. Fixed the problem of Claude cache writes going unbilled when they were not split into 5-minute and 1-hour amounts. The unsplit part is billed as 5-minute writes.
  • Price sync: Added adjusting synced upstream prices by the site exchange rate. You can keep the source price, or multiply or divide by the rate. Models that already match can be selected and adjusted too.
  • Tasks: Fixed the problem of video tasks being refunded after 24 hours. The default wait is now 72 hours. A TASK_TIMEOUT_MINUTES you already set is left as it is. Fixed the problem of Kling billing the outer duration while generating the duration in metadata. Added file uploads on a plugin's own routes. Task plugins can read the client's request headers. Authorization and Cookie are not given to the plugin.
  • Streaming: Fixed the problem of a slow transfer of a large event being recorded as a disconnect. Fixed the problem of a finished Responses reply being logged as a disconnect. The usage is still recorded.
  • Also: Fixed the problem of structured output and tool parameters having their field order rearranged. They are sent in the client's order. Fixed the problem of Chat requests losing imageConfig on the way to Gemini, so image size and aspect ratio are kept. Fixed the problem of Advanced Custom dropping Pass Through Body on save. Fixed the problem of an edit drawer keeping the previous token or model when you switch records. Fixed the problem of access logs storing keys from the URL. Added copying model names from a usage log's details.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.46...v1.0.0-rc.47

下载资源


v1.0.0-rc.46

正式版本 · 发布于 2026-10-22 00:25:54 (中国时间)

[!IMPORTANT] 修复 CVE-2026-111943,请尽快升级。这一版用 Go 1.26.10。Go 校验证书时,会拒绝一小批已经不再可信的中间证书。用源码编译的,Go 也要换成 1.26.10。

Fixes CVE-2026-111943. Please upgrade soon. This release runs on Go 1.26.10. When Go checks a certificate, it rejects a small set of intermediate certificates that are no longer trusted. Builds from source need Go 1.26.10 too.

中文

  • 安全:修复 CVE-2026-111943。运行时改为 Go 1.26.10,校验证书时会拒绝一小批已经不再可信的中间证书。
  • 邮件:新增用 Resend 发邮件的功能,可以代替 SMTP。发件地址和发件人名称单独填。
  • 数据看板:新增缓存用量的显示,和总 token 放在一起。
  • 向量:新增阿里云百炼多模态向量模型 qwen3-vl-embedding 的支持,同系列的视觉向量模型也走这个接口。
  • 任务:修复任务换渠道重试时还按上一次价格计费的问题。更贵的渠道会先补预扣,余额不够就不会发出去。修复任务提交和轮询没用上「请求头覆盖」的问题。修复轮询跳到别的地址时密钥跟着过去的问题。
  • 渠道:修复可灵不接受单个密钥的问题。插件 1.1.1,不带竖线的密钥可以直接用。修复 DeepSeek 美元余额是 0、人民币有钱时,余额显示成 0 的问题。
  • 修复:修复通知限流每到整点就重新计数的问题,超过 60 分钟也按你设的时长算。修复 Claude 流式请求在准备和重试期间断开的问题。修复连续的助手消息合并后丢掉工具调用、Claude 报错的问题。修复 Redis 清掉脚本后限流失效的问题。发给 Gemini 的向量请求里带了图片或视频时,会直接拒绝,不再计费。

English

  • Security: Fixed CVE-2026-111943 by moving to Go 1.26.10. Certificate checks reject a small set of intermediate certificates that are no longer trusted.
  • Email: Added Resend for sending mail, in place of SMTP. The sender address and sender name are set on their own.
  • Dashboard: Added cache usage next to the total token count.
  • Embeddings: Added Alibaba Bailian multimodal embeddings, starting with qwen3-vl-embedding. The other vision embedding models on Bailian use the same endpoint.
  • Tasks: Fixed a retry on another channel still using the previous price. A more expensive channel reserves the difference first, and is not called when the balance cannot cover it. Fixed task submission and polling ignoring Request Header Override. Fixed polling redirects carrying the key to another address.
  • Channels: Fixed Kling rejecting a single key. Plugin 1.1.1 accepts a key with no vertical bar. Fixed DeepSeek balance showing 0 when the USD wallet is 0 and the CNY wallet has money.
  • Fixes: Fixed notification rate limits resetting at each hour, so a window longer than 60 minutes lasts for the time you set. Fixed Claude streams dropping during preparation and retries. Fixed merged assistant messages dropping tool calls, which made Claude reject the request. Fixed rate limiting after Redis flushed its scripts. An embedding sent to Gemini with an image or video is rejected and not billed.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.45...v1.0.0-rc.46

下载资源


v1.0.0-rc.45

正式版本 · 发布于 2026-10-17 23:42:41 (中国时间)

[!IMPORTANT] v1 正式版即将发布,现在是最后几个 RC 版本。新增 DeepSeek V4.1 Flash、Search 和 Fetch,通知分开开关,以及拖动排列渠道优先级的功能。

敏感词过滤默认关着。以前填过敏感词、但没保存过这个开关的,升级后到「请求检查」里打开。

v1 is coming soon. These are the last few release candidates. Added DeepSeek V4.1 Flash, Search and Fetch, separate notification switches, and dragging to set channel priority.

Sensitive word filtering is off by default. If you filled in a word list and never saved the switch, turn it on under Request checks after upgrading.

中文

  • DeepSeek:新增 DeepSeek V4.1 Flash(deepseek-flash)和 deepseek-v4-pro 的支持,后面可以加 -none、-low、-max,@thinking 和 @effort 也能用。新增 Search 和 Fetch,地址是 /v1/tools/search 和 /v1/tools/fetch。Claude Code 和 Codex 让 DeepSeek 去搜索、打开网页时,按次数计费,每 1000 次 0.75 美元。
  • 通知:新增按种类开关通知的功能,余额不足提醒默认开着。验证码、重置密码、绑定邮箱,看 SMTP 有没有配好。余额低于你设的数时提醒一次,充回去之后,下次再低才会再提醒。
  • 渠道:新增拖动调整渠道优先级的功能,在渠道列表打开「拖拽模式」。新增 New API 渠道查询上游余额的功能,也可以绑定海螺、Vidu 和 Veo。新增令牌「允许查询用户额度」,新建的默认开着,以前建的还是关的。
  • 限流和计费:修复分组限流算到一起的问题,某个分组自己设了限流,就按这个分组的次数算。修复 Vidu 收费和实际生成对不上的问题,按它实际生成的模型、时长和分辨率计费。修复 Claude 流式把上游报的 0 丢掉的问题,报了 0 就按 0 算。提示词全在缓存里时,按读缓存的价格计费。
  • 报错:修复请求内容读失败时看不出原因的问题。上游报错里,你填的地址、IP 和密钥会被藏起来,文档链接和邮箱还看得到。
  • 其他:新增 Sub2API 查询余额的功能。新增 AWS 的 Mantle(Messages API),已经在用的还是 InvokeModel。新增 Vertex 用 API Key 时填写项目 ID 的功能。任务插件这一版更快。
  • 修复:修复 Vertex 的 us、eu 访问地址错误的问题。修复容器里过载保护看错 CPU 和内存的问题,看的是容器自己的,连续大约 15 秒都过高才会拒绝请求。

English

  • DeepSeek: Added deepseek-flash and deepseek-v4-pro. You can add -none, -low, or -max, and @thinking and @effort work too. Added Search and Fetch at /v1/tools/search and /v1/tools/fetch. When Claude Code or Codex has DeepSeek search or open a page, that is charged per request, $0.75 per 1,000.
  • Notifications: Added a switch for each kind of notification. The low balance reminder starts on. Verification codes, password resets, and email binding go out when SMTP is set up. You get one reminder when the balance goes below the number you set, and another the next time it does, after a top-up.
  • Channels: Added dragging to change channel priority. Turn on Drag mode in the channel list. Added upstream balance checks for New API channels, which can also bind Hailuo, Vidu, and Veo. Added Allow querying user quota on tokens. New tokens start with it on. Older tokens stay off.
  • Rate limits and billing: Fixed group rate limits being counted together. A group with its own limit is counted on its own. Fixed Vidu charges that did not match the video it generated. The charge uses the model, duration, and resolution it actually made. Fixed Claude streams dropping a 0 from the upstream. A reported 0 stays 0. When the whole prompt is cached, the charge is the cache-read price.
  • Errors: Fixed request failures that hid the real reason the body could not be read. If it is too large, the response is 413. In an upstream error, the address, IP, and key you entered are hidden. Documentation links and email addresses stay visible.
  • Also: Added balance checks for Sub2API channels. Added Mantle (Messages API) for AWS channels. Ones already in use stay on InvokeModel. Added a project ID field for Vertex API Key mode. Task plugins are faster in this release.
  • Fixes: Fixed wrong Vertex addresses for the us and eu regions. Fixed overload protection in containers reading the wrong CPU and memory. It uses the container's own, and turns requests away only after they stay too high for about 15 seconds.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.44...v1.0.0-rc.45

下载资源


v1.0.0-rc.44

正式版本 · 发布于 2026-10-12 21:42:01 (中国时间)

[!IMPORTANT] v1 Coming Soon & Log Export / v1 即将发布与日志导出

v1 正式版即将发布,现在是最后几个 RC 版本。

使用日志支持导出 CSV。可以在日志维护里设置是否允许用户导出,以及日志最长时间范围,默认 365 天。普通用户的日志查询、导出和数据看板都按这个范围限制。

游乐场的数据按账号分开保存,升级后之前的聊天记录会清空一次。

Claude 请求按模型支持的档位发送思考强度。发给 Gemini 的工具和结构化输出保留完整的 JSON Schema。

v1 is coming soon. These are the last few release candidates.

Usage logs can be exported as CSV. In Log Maintenance you can choose whether users may export and set the longest log time range, 365 days by default. Regular users' log searches, exports, and dashboard charts all follow that range.

Playground data is stored per account. Earlier Playground history is cleared once after the upgrade.

Claude requests get the thinking effort each model accepts. Tools and structured output sent to Gemini keep their full JSON Schema.

New Features

  • The usage log page has an Export button next to Search. It downloads the current view, with the page's filters and a chosen time range, as a CSV file in the viewer's language. Users export their own logs, and administrators in the all-users view export every user's logs. Each user runs one export at a time, across tabs and, with Redis, across nodes (#7774).
  • Log Maintenance adds Allow users to export logs (on by default) and Longest log time range (days) (365 by default). Regular users' log searches had no limit before. Their searches, exports, and dashboard usage and traffic charts now share this range. The page is split into Log recording, Log search and export, history log cleanup, and server log management.
  • Date and time pickers, including the date range filter on log pages, work down to the second.

Fixes and Improvements

  • Known Claude models get the nearest thinking effort they accept, and none when they accept none. This fixes 400s on Opus 4.5 with max or xhigh, on Sonnet 4.5 and Haiku 4.5, and when a model suffix or modifier turns thinking off. Native Claude requests without a suffix or modifier pass through as sent.
  • Claude Haiku 5.5 uses adaptive thinking with medium effort by default. Converted requests drop temperature, top_p, and top_k for it. Gemini 2.5 Pro gets a 32768 thinking budget for xhigh and max.
  • Tools and structured output sent to Gemini keep const, oneOf, $ref, $defs, type arrays, and non-string enums. A schema that Gemini's typed Schema can hold is sent as before, and any other schema goes in parametersJsonSchema or responseJsonSchema. Models set to Gemini API v1 get a cleaned schema and a conversion warning (#7455, #7704).
  • Responses images sent to Chat Completions upstreams use the object form of image_url, so vLLM and strict gateways accept Codex screenshots and tool images (#7578).
  • Chat streams converted to Claude Messages keep answer text that arrives in the same chunk as the last reasoning token (#7664). Claude Messages converted to Chat Completions keep assistant text next to tool calls (#6871).
  • Claude requests forward thinking.block_binding and every anthropic-beta header value. This fixes "The block is bound to a different conversation" in multi-turn conversations whose system prompt or tools change (#7732).
  • Responses WebSocket sessions send a close frame when the server ends them, so Codex sees a normal close (#7642).
  • Without Redis, model rate-limit 429s carry the same error message and log line as with Redis (#7721).
  • The console reloads once when a page's code fails to load, and the error page shows a status code only when there is one (#7634).
  • The wallet, security, and OAuth callback pages and the user binding dialog load much less JavaScript. Linux DO bindings show the Linux DO logo.
  • Date pickers and relative times follow the interface language (#7654).
  • The model square shows the latest 24 hourly status samples within 7 days, with no gaps. Expression model cards show the cache read price (#7757).
  • Usage log previews keep the recorded billing tiers (#7763), and task settlement logs show tiered billing (#7446).
  • Pricing conversion accepts model metadata that declares endpoints as an array (#7724). Root can manage pricing while the model square is disabled (#7761).
  • Performance metrics count streams that finished before the client disconnected (#7638).
  • The Sign in button on password login stays clickable and shows the legal consent warning (#7771).
  • The Auto font uses the browser's sans-serif again. Meta Muse Spark models show the Meta icon (#7734), and billing source icons line up on mobile (#7760).
  • Dependency updates, including Electron 41.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.43...v1.0.0-rc.44

下载资源


v1.0.0-rc.43

正式版本 · 发布于 2026-10-10 14:11:03 (中国时间)

[!IMPORTANT] 完善了 i18n,控制台、API 错误、邮件、通知和服务器日志都支持多语言。使用 DEFAULT_LANGUAGE 环境变量设置默认语言,不设置时为英文。

渠道新增“忽略上游证书校验”开关,可以连接使用自签证书的上游。

任务插件新增 utils.fetch,可以读取上游数据。

豆包 Seedance 1.5 Pro、2.x 和万相 3.0 支持传 -1 自动选择时长,按上游回报的时长计费。

Improved i18n. Console messages, API errors, emails, notifications, and server logs are now multilingual. Set the default language with the DEFAULT_LANGUAGE environment variable. It defaults to English.

Channels have a new Skip Upstream TLS Verification switch for upstreams that use self-signed certificates.

Task plugins can read upstream data with the new utils.fetch.

Doubao Seedance 1.5 Pro and 2.x, and Wan 3.0, accept -1 to pick the video duration automatically and bill the duration the upstream reports.

New Features

  • Improved i18n. The web console shows API messages and log entries in all seven interface languages. The backend translates errors for AI clients, emails, and notifications into English, Simplified Chinese, or Traditional Chinese, using the account language first and then the request's Accept-Language header. Log entries written before this release keep their original text.
  • DEFAULT_LANGUAGE (en, zh-CN, or zh-TW) sets the default language of backend messages and server logs. It defaults to en.
  • Skip Upstream TLS Verification is under the HTTP settings of each channel. It covers the channel's relay requests, Responses and Realtime WebSocket, task submission and polling, plugin fetches, balance, usage, and model-list queries, and media proxied through the channel. Codex OAuth refresh and Vertex or plugin service-account tokens still verify certificates.
  • Task plugins can call utils.fetch in the submit, query, and content-download hooks. It reaches the channel Base URL and the additional request domains the plugin declares, and the upload dialog lists those domains. The Task Plugin API v1 document lists the hooks and limits.
  • Plugins can call utils.json.clone and export parseSubmitEventDelta with no capability declaration. Plugins that declare json-clone@1 or submit-sse-delta@1 keep loading.
  • Doubao 1.3.0 and Alibaba Bailian 1.4.2 accept a duration of -1 for Seedance 1.5 Pro and 2.x and for Wan 3.0. The request reserves the model's longest duration (12 seconds for Seedance 1.5 Pro, 15 for 2.0, 30 for 2.5 and Wan 3.0) and bills the duration the upstream reports. A JSON duration on /v1/videos now reaches Ark, and Wan 3.0 smart duration works on /v1/video/generations. (#7700)

Fixes and Improvements

  • Responses input converted for Claude and Gemini drops assistant text that comes after the last user message or tool result, and records a trailing_assistant_omitted warning. Codex sends such input when it retries a stream that failed after a reply finished. Claude 4.6 and later, Gemini 3.6 Flash, and Gemini 3.5 Flash-Lite and later rejected it with a 400. Chat Completions and Claude Messages requests keep their prefill.
  • xAI Grok Imagine 1.1.0 bills video edits and extensions at the output resolution. The output keeps the input video's resolution up to 720p. The plugin reads the output file header and bills 480p when the shorter side is 480 pixels or less. It bills 720p otherwise, and when the header cannot be read.
  • Hailuo 1.2.1 downloads MiniMax v1 videos through the file retrieve link. Those downloads returned 410 before. (#7709)
  • Multipart task submissions send the Content-Type of the rebuilt body, so the boundary matches the body the upstream receives. (#7655)

What's Changed

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.42...v1.0.0-rc.43

下载资源


v1.0.0-rc.42

正式版本 · 发布于 2026-10-08 18:10:46 (中国时间)

[!IMPORTANT] Search Billing & Task Plugins / 搜索计费与任务插件

重做了搜索函数计费。渠道可以按上游自己的方式进行网络搜索,并按上游回报的搜索次数计费。

任务插件性能大幅提升。支持插件决定是否保留 JSON 字段顺序,声明 json-order@1 即可;其他插件行为不变。

高级自定义渠道可以把 Claude Messages 和 Gemini 转到 OpenAI Responses。

新增 xAI Grok Imagine 视频任务插件。

Search-function billing has been reworked. Channels can encode Web search for their upstream and settle from the search counts the vendor reports.

Task Plugins are substantially faster. A plugin that must keep the client’s JSON field order can declare json-order@1. Other plugins are unchanged.

Advanced Custom channels can convert Claude Messages and Gemini to OpenAI Responses. An xAI Grok Imagine video Task Plugin is added.

New Features

  • Reworked search-function billing, including per-Channel Web search encoding and vendor-reported search counts.
  • Advanced Custom channels can convert Claude Messages and Gemini generateContent to OpenAI Responses.
  • Moonshot Channels forward /v1/responses unchanged. Kimi currently serves kimi-k3 on that path.
  • Added the xAI Grok Imagine video Task Plugin: grok-imagine-video, grok-imagine-video-1.5, and grok-imagine-video-1.5-lite.
  • Advanced parameter overrides support Regex conditions (#7698).
  • Users can be filtered by User Group.
  • Task Plugins that declare json-order@1 keep the client’s JSON field order through to the upstream.

Fixes and Improvements

  • Task Plugin requests are substantially faster, including passthrough submissions.
  • Token counting is much faster, including long text without punctuation.
  • Gemini stream usage is no longer multiplied by the number of frames (#7687).
  • Responses tool-output images are sent to Gemini as images, not as text. Claude Opus 5.5 defaults to medium effort when the client sets none.
  • Responses custom tools such as exec and apply_patch are kept on Claude and Gemini upstreams (#7636).
  • Turning off the Thinking Suffix Adapter now also leaves effort suffixes such as -high unchanged.
  • Completed image generations still bill when the Responses request later fails or is cancelled.
  • Frontend build files no longer count against the page rate limit, so a cold load does not return 429 for the next session on the same IP.
  • gpt-6-sol and gpt-6-luna use max_completion_tokens (#7559).
  • System Settings are hidden from non-root admins (#7513).
  • Fixed a blank Channels page on OriginOS 6. Fixed rounded clipping of Group names on API Keys (#7645).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.41...v1.0.0-rc.42

下载资源


v1.0.0-rc.41

正式版本 · 发布于 2026-09-30 21:09:14 (中国时间)

[!IMPORTANT] Access Tokens & Task Plugins / 访问令牌与任务插件

安全与访问里的单个面板访问令牌,改为最多 20 个具名访问令牌。创建时只显示一次,默认 30 天过期;作用域按本人已有权限勾选。升级后旧版令牌还能再用 30 天,之后会被拒绝,且不能重新生成,请在到期前换成新令牌。

管理员管理用户时,删除、改状态或角色、设置密码或权限、创建管理员、重置通行密钥、关闭两步验证、清除绑定,都需要一次性校验。额度调整,以及修改显示名、分组、备注,不需要。

任务插件改由 moejs 运行,性能大幅提升,插件接口不变。

豆包 Seedream 图片改走任务插件的 OpenAI Images(/v1/images/generations、/v1/images/edits)。新增 Seedream 5.0 Flash;各模型按自己的档位计价。任务插件收窄用量项之后,已保存的价格仍可编辑。

Security & Access replaces the single dashboard Access Token with up to 20 named Access tokens. A token is shown once at creation, expires in 30 days by default, and its Scopes stay within what the owner can already do. The Legacy token keeps working for 30 days after the upgrade, then it is rejected and cannot be regenerated. Replace it before then.

Admin user management now requires a single-use verification for delete, status or role changes, password or Permissions, creating an admin, resetting a Passkey, disabling 2FA, and clearing a binding. Quota adjustments, and edits to display name, Group, or remark, do not.

Task Plugins now run on moejs, with a large performance improvement.

Doubao Seedream images now go through the Task Plugin OpenAI Images paths (/v1/images/generations, /v1/images/edits). Seedream 5.0 Flash is added, and each model is priced on its own tiers. Prices saved before a Task Plugin narrows its usage facts stay editable.

New Features

  • Replaced the single dashboard Access Token with up to 20 named Access tokens on Security & Access. Tokens are shown once, use Scopes, and expire after 30 days by default.
  • Access tokens can be renamed without verification. Changing Permissions requires a single-use proof bound to that token.
  • Moved Task Plugins to moejs, with a large performance improvement. The plugin API is unchanged.
  • Added Seedream 5.0 Flash, and price each Seedream model on its own tiers. Seedream images are served through the Task Plugin OpenAI Images protocol.
  • Highlight differing values when comparing source price expressions (#7543).
  • Added a Refresh button on the Channels table.

Fixes and Improvements

  • Keep Pricing Configuration editable after a usage profile drops facts. Remaining prices stay in place.
  • Keep Responses custom tools when converting to Chat Completions, so tools such as exec and apply_patch are no longer dropped.
  • Preserve Claude auto-mode safeguards and per-message output_config (#7598, #7561).
  • Preserve the Responses WebSocket setting when saving a Channel (#7468).
  • Revalidate Marketplace downloads so a republished plugin source does not fail the integrity check from a stale cache.
  • Reject non-standard roles when creating a user.
  • Release binaries now embed the real version instead of v0.0.0 (#7536).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.39...v1.0.0-rc.41

下载资源


v1.0.0-rc.40

正式版本 · 发布于 2026-09-21 23:15:58 (中国时间)

[!IMPORTANT] Task Plugins / 任务插件

任务插件源码上限提高到 8 MiB,更大的插件可以正常上传和保存。 上游提交返回 201 / 202 等成功状态时,任务会正常继续,不再被当成失败。

定价配置在任务插件收窄可选项后,仍可编辑剩下的档位和价格,不会整表打不开。 Claude / Responses 里工具结果中的图片会按图片送给上游,不再当成文本。

Task Plugin source uploads now allow up to 8 MiB, so larger plugins can be saved. A 2xx upstream submit status such as 201 / 202 is accepted, so the task continues instead of failing.

Pricing Configuration stays editable after a Task Plugin narrows its options; remaining tiers keep their prices. Images in Claude / Responses tool results are sent upstream as images, not as text.

New Features

  • Raised the Task Plugin source upload limit to 8 MiB. After upload, Activate now is available.
  • Accept any 2xx upstream status on task submission, including 201 Created and 202 Accepted (#7478).

Fixes and Improvements

  • Keep Pricing Configuration editable after a Task Plugin drops enum values. Unreachable branches are skipped; remaining prices are preserved.
  • Send Claude tool_result images and Responses tool-output media upstream as images, not as text (#7512, #7510).
  • Keep upstream metadata in Alibaba OpenAI Images render (#7507).
  • Resolve safe constants in plugin metadata previews. Isolate theme preferences in local storage. Include provider icons in Windows builds.

What's Changed

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.39...v1.0.0-rc.40

下载资源


v1.0.0-rc.39 - Task Plugins & Quota Settings

正式版本 · 发布于 2026-09-20 22:27:48 (中国时间)

[!IMPORTANT] Task Plugins & Quota Settings / 任务插件与额度设置

任务插件现已兼容 OpenAI Images: 可承接 /v1/images/generations 和 /v1/images/edits。 请求内提交任务并等待完成后,按 OpenAI 图片格式返回。 阿里云百炼万相图片模型改走任务插件;豆包 Seedream 图片生成已接入。

New API 渠道可绑定多个上游任务插件,用于对接另一套网关里的多个任务插件。 渠道的模型重定向更清晰,应用上游模型变更前可先预览。

额度设置可配置钱包免预扣门槛和输入预扣倍率,余额足够时跳过预扣。

Task Plugins now serve OpenAI Images: /v1/images/generations and /v1/images/edits. The host submits the task, waits inside the request, and returns an OpenAI image response. Unclaimed models still use the existing image relay. Alibaba Bailian Wanxiang image models now go through Task Plugins. Doubao Seedream image generation is added.

A New API Channel can bind multiple Upstream task plugins, for another gateway that hosts several Task Plugins. Model Mapping is clearer, and upstream model changes can be previewed before apply.

Quota Settings add Wallet pre-consume bypass threshold, and Input pre-consume multiplier. High enough balances skip pre-consume.

New Features

  • Task Plugins can serve OpenAI Images (/v1/images/generations, /v1/images/edits). Bailian Wanxiang image models now go through the Alibaba Task Plugin. Doubao Seedream image generation is added.
  • New API Channels can bind multiple Upstream task plugins.
  • Quota Settings: Wallet pre-consume bypass threshold (USD) and Input pre-consume multiplier.
  • Model management Sync metadata supports bulk field selection.
  • API Keys can show and copy the Default API address / Current domain.
  • Group configuration supports drag sorting and a clearer editor.
  • Usage Logs show billing source and task artifacts for Task Plugin image work. Async tasks record performance metrics when they reach a terminal status.

Fixes and Improvements

  • Seedance and Wan Task Plugins price only the resolutions each model actually offers. Unsupported resolutions are rejected at submit.
  • Preview upstream model changes before applying them. Model Mapping controls are simpler.
  • Display conditional task billing prices more reliably. Accept fractional Group ratios and tool prices. Limit pricing inputs to four decimal places (#7453).
  • Derive Response model mismatch from model names (#7464). Restore compact cost bubbles and hide funding-source labels when Subscription is not in use (#7450, #7451).
  • Forward reasoning_effort to Zhipu (#7124). Keep mobile dialog actions on screen. Start linked-account verification from the provider button.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.38...v1.0.0-rc.39

下载资源


v1.0.0-rc.38 — Responses WebSocket & Request Policies

正式版本 · 发布于 2026-09-18 23:23:26 (中国时间)

[!IMPORTANT] Request Policies & Channels / 请求策略与渠道

系统设置新增请求策略:集中配置请求检查、会话与重试、渠道健康,并在使用日志中留下策略决策记录。

渠道创建与编辑补充快捷选项、透传说明,以及模型重定向工作台。高级自定义渠道可按路径单独开启透传。新增 vLLM、SGLang 渠道;Ollama 渠道可按渠道开启 OpenAI 兼容对话。

渠道可开启 Responses WebSocket。高级自定义、Sub2API、New API 渠道在开关打开后可用;高级自定义仅用于无转换的 /v1/responses。

System Settings now includes Request policies: Request checks, Sessions and retries, and Channel health, with policy decision records on Usage Logs.

Channel create and edit add Quick options, Pass-through guidance, and a Model Mapping workbench. Advanced Custom channels can enable Pass-through per path. vLLM and SGLang channels are added. Ollama channels can enable OpenAI-compatible chat per Channel.

Channels can enable Responses WebSocket. Advanced Custom, Sub2API, and New API channels can use it when the toggle is on. Advanced Custom only uses converter-free /v1/responses paths.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

New Features

  • Added Request policies in System Settings: Request checks, Sessions and retries, and Channel health, with policy decision records on Usage Logs.
  • Added Responses WebSocket relay, with a per-Channel toggle. Advanced Custom, Sub2API, and New API channels can use it when enabled; Advanced Custom only uses converter-free /v1/responses.
  • Added a Model Mapping workbench, Quick options, and Pass-through controls in the Channel editor. Advanced Custom channels can enable Pass-through per path.
  • Added vLLM and SGLang channels. Ollama channels can enable OpenAI-compatible chat per Channel.
  • Added filtered task history and cleanup in System Info.
  • Show subscription deductions on Usage Logs, and flag Response model mismatch when the upstream model differs.

Fixes and Improvements

  • Interrupted Responses streams no longer settle at zero and refund the whole pre-consume Quota; estimated usage is billed unless upstream reported an explicit failure (#7427).
  • Count Images by payload for Quota, and map image output token details into image-output billing (#7410).
  • Hailuo / MiniMax Task Plugins bill only the dimensions each model family supports.
  • Reserve model rate-limit slots and judge success by the response outcome, not HTTP status alone.
  • Hide Task Plugin keys from the public no-Channel 503, while keeping plugin context for operators (#7414).
  • Reject Gemini :countTokens as an unknown path instead of treating it as generateContent (#7388).
  • Request stream usage on every cross-protocol conversion to OpenAI chat (#7389).
  • Preserve Ollama tool calls from the final stream frame (#7376).
  • Restore saved compatible Passkey domains; fix DeepSeek Channel balance fetch (#6814); accept mixed-case audio extensions (#7321).
  • Handle legacy database constraints and scoped authorization policies on upgrade.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.37...v1.0.0-rc.38

下载资源


v1.0.0-rc.37- Pricing Configuration, Task Plugins, and Passkey

正式版本 · 发布于 2026-09-11 23:21:39 (中国时间)

[!IMPORTANT] Pricing Configuration & Task Plugins / 定价配置与任务插件

旧定价模式即将弃用。定价配置可将当前价格转换为计费表达式草稿,预览生效价格后再保存。新编辑器支持按条件计价、按次、含时间条件,以及图片用量与图片缓存。gpt-image-2、gpt-image-2.5-sunburst、gpt-image-2.5-flare 已有内置计费表达式默认值;已有管理员覆盖仍然优先。

任务插件能力增强:支持流式输出;定价配置可按任务插件设置用量价格与计费表达式;插件详情展示更新日志,缺省回退英文。创建与编辑渠道时,任务插件可参与提供商与模型选择,并带出对应插件信息。

渠道的创建与编辑已统一:共用提供商选择、分页配置、模型发现、模型重定向与参数覆盖。创建渠道时会优先使用已可用的任务插件。

安全与访问支持多个通行密钥域名。通行密钥只认创建它的网站。移除仍在使用的域名会先预览受影响数量,并要求确认;被移除域名上的通行密钥将无法继续使用。

Legacy pricing will be deprecated soon. Pricing Configuration can convert current prices to an Expression draft; review the effective prices, then save to apply. The editors now support Pricing by condition, Per-request, Time-based, and image usage / image cache. gpt-image-2, gpt-image-2.5-sunburst, and gpt-image-2.5-flare have built-in Expression defaults; existing administrator overrides still take precedence.

Task Plugins capabilities are expanded: Streaming; Usage prices and Expression in Pricing Configuration per Task Plugin; and Changelog in plugin details with an English fallback. When creating or editing a Channel, Task Plugins can take part in provider and model selection and bring along the matching plugin info.

Channel create and edit are unified: shared provider selection, tabbed setup, model discovery, Model Mapping, and parameter overrides. Channel creation prefers an available Task Plugin.

Security & Access supports multiple Passkey domains. Passkeys only work on the website they were created for. Removing a domain still in use previews how many Passkeys are affected and requires confirmation; Passkeys on a removed domain will stop working.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

New Features

  • Added Convert to expression in Pricing Configuration: review a legacy-to-Expression draft with effective prices, then save to apply it. Legacy pricing will be deprecated soon.
  • Extended Expression editors and usage details: Pricing by condition, Per-request, Time-based, and image usage / image cache. Confirmation is required before replacing an Expression.
  • Added built-in Expression defaults for gpt-image-2, gpt-image-2.5-sunburst, and gpt-image-2.5-flare, including separate text and image cache prices. Existing administrator overrides stay in place.
  • Expanded Task Plugins capabilities: Streaming, Usage prices and Expression per Task Plugin, and localized Changelog (English fallback).
  • Unified Channel create and edit: shared provider selection, tabbed setup, inline model discovery, Model Mapping, and parameter overrides.
  • Let Task Plugins take part in Channel provider and model selection, including a gateway category and preferring available plugins for legacy task providers.
  • Added System updates reminders for administrators.
  • Added multiple Passkey domains in Security & Access, with impact preview and confirmation before removing a domain still in use.

Fixes and Improvements

  • Validate image quantities before reserving Quota, and keep image usage consistent through reservation, retries, and settlement.
  • Stop Pricing Configuration writes from resetting or failing to persist on some long-lived deployments.
  • Allow editing multi-key selection strategy without dropping existing keys; omit the strategy for single-key Channels.
  • Restore the add split button in Advanced Custom (#7289).
  • Correct Wan model protocols and usage accounting; preserve provider fields in Sora video queries; fix VolcEngine Channel model-list fetch (#7203).
  • Unify server error notifications so each failed operation is reported once, while preserving backend details.
  • Deduplicate /api/status requests (#7189).
  • Keep Model pricing content in one scroll area.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.36...v1.0.0-rc.37

下载资源


v1.0.0-rc.36 - Task Plugins, Pricing Configuration, and Quota

正式版本 · 发布于 2026-09-08 21:01:52 (中国时间)

[!IMPORTANT] Task Plugins & Pricing / 任务插件与定价

本版本完善任务插件与插件市场:插件图标、插件官网、插件元数据与能力,创建渠道时可带出对应插件信息。同时改进模型管理、目录展示与广场展示、定价配置,以及 API 密钥与用户额度、使用日志、兑换码。定价货币可切换为站点货币以便录入和查看,额度仍按美元扣费。

This release improves Task Plugins and the Marketplace: Plugin icon, Plugin website, Plugin metadata, and Capabilities, plus matching plugin info when creating a Channel. It also improves Model management, Catalog visibility, Model square visibility, Pricing Configuration, Quota on API Keys and users, Usage Logs, and Redemption Codes. Pricing currency can switch to Site currency for entry and review; Quota is still deducted in USD.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

New Features

  • Improved Task Plugins and the Marketplace: Plugin metadata, Plugin website, Plugin icon (including optional icon.svg / icon.png), integrity checks, Capabilities, and clearer install/update flows.
  • Improved Channel setup for Task Plugins so a new Channel picks up the matching Plugin icon and Plugin metadata.
  • Added Site currency in Pricing Configuration. Display and conversion use the site exchange rate; stored prices remain in USD.
  • Improved Model management, pricing display, Catalog visibility, and Model square visibility. Channel-configured models appear without creating catalog metadata first. The Model square can show Pricing by condition, usage prices, and visibility reasons.
  • Added a searchable Group filter on Usage Logs. Suggestions come from the current view; historical Group names can still be typed in.
  • Refined the Usage Logs mobile layout so filters and quick actions stay available.
  • Refined Quota display on API Keys and users: Remaining quota and used amounts, progress bars, Group ratio badges, and activity timestamps. Full API Keys are resolved only for explicit copy or chat actions.
  • Added confirmed batch deletion for Redemption Codes, plus an optional Save as a file step (TXT / Markdown) after creation.

Fixes and Improvements

  • Show desktop API Keys Remaining quota and used amounts side by side, with more room and consistent cell spacing. Mobile stacked labels are unchanged.
  • Unified table cells and Quota details across list pages.

Full Changelog: v1.0.0-rc.35...v1.0.0-rc.36

下载资源


v1.0.0-rc.35 — Wan 3.0 Video, Plugin Routing

正式版本 · 发布于 2026-09-07 22:45:50 (中国时间)

[!IMPORTANT] Task Plugin Controls / 任务插件控制简化

任务插件现在只有两层开关:总开关与每个插件自己的开关。关闭某个插件后,不会再回退到同名内置插件,同名模型也不会再继续由内置插件处理。内置插件会按请求中的模型名回显(遵循模型重定向),而不是上游真实 ID。

Task plugins now have two control layers only: the master switch and each plugin’s own toggle. Disabling a plugin no longer falls back to a same-name built-in plugin, so same-name models are no longer still handled by the built-in plugin. Built-in plugins echo the requested model name (honoring model redirects) instead of the upstream model ID.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

New Features

  • Added Alibaba Bailian wan3.0-video and wan3.0-video-prime all-in-one video models, with DashScope media, resolution/ratio, duration rules, and billing ratios.
  • Supported wan3.0 smart duration (duration / seconds = -1): submit -1 upstream, pre-consume 30 seconds, then settle from actual usage. Other Wan models reject this marker instead of silently defaulting to 5 seconds.
  • Added kimi-k3 to the Moonshot model list.

Fixes and Improvements

  • Preserved Kimi K3 mid-conversation tool-loading messages, so dynamic tools are no longer dropped during relay and tool_choice=required no longer fails for missing tools (#7235).
  • Made wan3.0 convert and billing follow the redirected upstream model, reject unknown sizes, restore the image-only guard for text-to-video models, and forward ratio/audio in native passthrough (#7240).
  • Made the SunoAPI built-in honor model redirects and fixed lyrics/music rendering. Bumped sunoapi to 1.0.2.
  • Replaced the model-card health strip’s last-three-bucket rates with an hourly series, so empty hours stay gray and the 24-slot bar can show a full day.
  • Portaled Combobox and Select popups into drawer content so they stay clickable inside modal drawers.
  • Switched the pricing card grid (and its skeleton) to three columns at the xl breakpoint.
  • Routed common and relaykit JSON helpers through a host-injectable codec so the JSON engine can be swapped in one place.

Full Changelog: v1.0.0-rc.34...v1.0.0-rc.35

下载资源


v1.0.0-rc.34

正式版本 · 发布于 2026-09-06 22:53:49 (中国时间)

[!IMPORTANT] Account Security / 账户安全功能完善

本版本补齐账户安全能力:登录与敏感操作共用校验流程;已登记的 TOTP 与 Passkey 可作为互备因子;系统访问令牌支持查看、轮换、撤销与访问记录;新增独立审计日志。注销账户、绑定、改密、Passkey/2FA 登记与渠道密钥查看均需作用域一次性证明,并绑定到发起会话。

Telegram 登录已迁到统一 OAuth。管理员须在 BotFather Login Widget 中登记 /oauth/telegram,并填写 Client ID / Client Secret 后重新启用;已有绑定会保留。密码存储改为默认 Argon2id(兼容历史 bcrypt),是本次安全加固的一部分,而非单独的升级动作。

This release completes account security: login and sensitive operations share one verification flow; enrolled TOTP and Passkey are alternative factors; system access tokens support status, rotation, revocation, and access history; and a dedicated audit log is added. Account deletion, bindings, password changes, Passkey/2FA enrollment, and channel-key access require scoped, single-use proofs bound to the initiating session.

Telegram login now uses unified OAuth. Administrators must register /oauth/telegram in BotFather’s Login Widget and enter the Client ID / Client Secret before re-enabling it; existing bindings are preserved. Password storage now defaults to Argon2id (with bcrypt-compatible reads) as part of this hardening, not as a standalone upgrade.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

New Features

  • Reworked model and vendor management: catalog metadata validation, vendor management, batch delete with channel/pricing cleanup, model pricing snapshot editing with optimistic concurrency, and upstream ratio sync with price cells. The models page is organized around vendors and model connections, with dedicated pricing and vendor-management dialogs.
  • Moved account security settings to a dedicated page, with system access-token status, rotation, revocation, and access history. Generate and revoke require scoped, single-use verification.
  • Added a dedicated audit log page (audit.read). Successful and failed API token and quota operations are recorded with role snapshots and safe metadata, correlated with top-up records. Model, vendor, and pricing mutations are also audited.
  • Unified login and sensitive-operation verification: enrolled TOTP and Passkey are alternative factors. Every primary login transport is gated before a session is issued; WebAuthn requires user verification; login challenges are consumed atomically with session creation.
  • Required a scoped, single-use proof for account deletion, rechecked the session inside the deletion transaction, and revoked all sessions afterward. Bindings, password changes, Passkey/2FA enrollment, and channel-key access are likewise bound to the initiating session and action.

Security

  • Completed the account-security surface: shared verification UI, session-bound proofs, last usable login method preservation, and audit of security operation outcomes. OAuth callback secrets are redacted from logs.
  • Applied Unicode-aware password length limits (8–128). New passwords default to Argon2id; existing bcrypt hashes remain valid. Profiles return has_password from the existing SELECT without extra queries.
  • Migrated Telegram login, binding, and security verification to the unified OAuth flow (authorization code + PKCE + ID tokens). Legacy widget / bind endpoints have been removed. A custom OAuth provider must not use the reserved telegram slug.

Fixes and Improvements

  • Fixed OpenAI Chat capability detection: match gpt-<n> by major version (n >= 5) so later generations such as gpt-6-astra use max_completion_tokens and drop unsupported temperature / top_p / logprobs. gpt-4.1, gpt-4o, gpt-oss, gpt-image, and gpt-realtime are unchanged (#7211).
  • Upgraded the SQLite GORM driver to distinguish unique indexes from constraints, and normalized equivalent MySQL decimal defaults and PostgreSQL CHAR metadata. Unchanged databases no longer emit redundant DDL on restart.
  • Bulk-copied RawMessage fields to reduce request deep-copy cost (#7221).
  • Collapsed the completed setup guide by default so it no longer occupies the dashboard.
  • Upgraded the ClickHouse driver to v2.46.0.

Full Changelog: v1.0.0-rc.33...v1.0.0-rc.34

下载资源


v1.0.0-rc.33

正式版本 · 发布于 2026-09-05 11:54:42 (中国时间)

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

[!IMPORTANT] OpenRouter Compatibility / OpenRouter 兼容性说明

OpenRouter 渠道不再将任意以 -thinking 结尾的模型名自动解释为思考模式别名,以避免错误改写 kimi-k2-thinking 等真实模型 ID。

依赖旧行为的用户应改用 some-model@thinking:on,或通过渠道模型映射保留原有公开名称:{"some-model-thinking":"some-model@thinking:on"}。符合模型家族识别规则的 Claude 与 Gemini 旧式思考后缀仍受支持。

OpenRouter channels no longer interpret arbitrary model names ending in -thinking as reasoning aliases, preventing real model IDs such as kimi-k2-thinking from being rewritten.

If you relied on the old behavior, use some-model@thinking:on, or preserve the old public name with channel model mapping: {"some-model-thinking":"some-model@thinking:on"}. Recognized Claude and Gemini family thinking aliases remain supported.

New Features

  • Added gpt-6-astra to the OpenAI model list with built-in expression pricing for standard and long-context requests, including input, output, cache-read, and cache-write usage. Existing administrator pricing overrides take precedence.
  • Added explicit trailing @key:value model modifiers for non-pass-through relay requests:
    • @thinking:on, @thinking:off, @thinking:adaptive, or @thinking:<budget>
    • @effort:none|minimal|low|medium|high|xhigh|max
    • @temperature:<number> and @topp:<number>
  • Model modifiers override corresponding request-body fields and remain effective across channel model mapping. Modifiers on the mapped model take precedence over those on the requested model; repeated keys use the rightmost value.
  • Added administrator-visible conversion diagnostics for modifier conflicts, duplicates, and provider-specific adjustments.
  • Added re:-prefixed Go regular expressions to Models that skip thinking suffix processing, allowing real model names containing @key:value to bypass modifier parsing and validation. Unknown modifier keys and invalid values otherwise return HTTP 400.

Billing and Routing

  • Added canonical billing names such as base@effort:high@thinking:on and base@thinking:on, with fallback to the base model when no matching variant price is configured.
  • Equivalent modifier variants share canonical pricing names. Numeric thinking-budget values, temperature, and topp do not create separate canonical pricing variants.
  • Updated pricing settings and pricing synchronization to expose the effective built-in billing defaults used at runtime.
  • Improved channel selection, model mapping, and token model-limit matching for models with modifiers or supported legacy aliases.
  • Preserved existing legacy alias pricing and Gemini thinking-budget wildcard entries.

Fixes and Improvements

  • Fixed implicit reasoning-effort remapping: max and xhigh now remain distinct through OpenAI Chat and Responses conversion paths.
  • Preserved native reasoning controls when no model modifier or protocol conversion requires adaptation, avoiding unnecessary normalization or rejection of provider-native values.
  • Restricted generic legacy suffix parsing to recognized GPT/o-series, Claude, and Gemini model families, protecting real model names such as qwen-max and kimi-k2-thinking.
  • Applied thinking-suffix exemptions consistently across DeepSeek, Volcengine, and xAI adaptors.
  • Improved Claude reasoning conversion by adapting unsupported combinations where possible and recording diagnostic warnings.
  • In global or channel-level pass-through mode, model modifiers are forwarded unchanged without local parsing or validation.
  • Improved HTTP 503 messages for models claimed by task plugins: errors now identify the claiming plugin and explain when it has no enabled channel in the selected group. Plugin model ownership remains unchanged (#7185).
  • Fixed release builds selecting an incorrect version by resolving the version from the triggering Git tag.

Full Changelog: v1.0.0-rc.31...v1.0.0-rc.33

下载资源


v1.0.0-rc.32

正式版本 · 发布于 2026-09-05 00:08:45 (中国时间)

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

[!IMPORTANT] Compatibility Notes / 兼容性说明

此前 OpenRouter 渠道会将所有以 -thinking 结尾的模型名解释为思考模式别名。该行为现已移除,以避免错误改写 kimi-k2-thinking 等真实模型 ID。

依赖旧行为的用户应改用 some-model@thinking:on,或通过渠道模型映射保留原有公开名称:{"some-model-thinking":"some-model@thinking:on"}。Claude 与 Gemini 模型家族原有的思考后缀仍然兼容。

v1.0.0-rc.31 引入的 POST /v1/messages/count_tokens 端点在本版本中暂时停用。

The previous OpenRouter-specific behavior that interpreted every model name ending in -thinking as a reasoning alias has been removed, preventing real model IDs such as kimi-k2-thinking from being rewritten.

If you relied on the old behavior, use some-model@thinking:on, or preserve the old public name with channel model mapping: {"some-model-thinking":"some-model@thinking:on"}. Existing Claude and Gemini family aliases remain supported.

The POST /v1/messages/count_tokens endpoint introduced in v1.0.0-rc.31 is temporarily disabled in this release.

New Features

  • Added explicit trailing model modifiers for non-pass-through relay requests:
    • @thinking:on, @thinking:off, @thinking:adaptive, or @thinking:<budget>
    • @effort:none|minimal|low|medium|high|xhigh|max
    • @temperature:<number> and @topp:<number>
  • Model modifiers override the corresponding request-body fields and remain effective across channel model mapping. Modifiers configured on the mapped model take precedence over those on the requested model.
  • Added conversion diagnostics for overridden, duplicated, or adjusted reasoning and sampling settings. These warnings are recorded with consumption logs for troubleshooting.
  • Unknown modifier keys and invalid values now return HTTP 400.
  • Added re:-prefixed Go regular expressions to Models that skip thinking suffix processing, allowing real model IDs containing @key:value segments to bypass modifier parsing and validation.

Billing and Routing

  • Added canonical billing identities for model variants. Pricing can now target forms such as base@effort:high@thinking:on or base@thinking:on, with automatic fallback to the base model.
  • Canonical billing is independent of modifier order, duplicate modifiers, and numeric thinking-budget values. temperature and topp never affect the selected billing identity.
  • Updated channel selection, model listing, model mapping, and token model-limit checks to recognize the underlying base model when modifiers or supported legacy aliases are used.
  • Preserved existing wildcard pricing behavior for legacy Gemini thinking-budget model names.

Relay Improvements

  • Limited legacy -thinking, -nothinking, thinking-budget, and effort suffix parsing to recognized GPT/o-series, Claude, and Gemini model families, preventing ordinary model IDs such as qwen-max from being misinterpreted.
  • Improved Claude reasoning conversion by safely adapting unsupported thinking modes, effort levels, budgets, and sampling combinations while recording conversion warnings.
  • Native Claude and Gemini requests without host-specific model modifiers continue to preserve their provider-native reasoning controls.
  • Global and channel-level pass-through requests remain byte-identical: model modifiers are not parsed or validated and are forwarded verbatim.

Bug Fixes

  • Improved task-plugin HTTP 503 errors to identify the plugin that owns the requested model when it has no enabled channel in the selected group. The error now recommends disabling or overriding the claiming plugin instead of returning only a generic “no available channel” message (#7185).
  • Fixed release builds resolving an incorrect version when the workflow is triggered from a tag.

Full Changelog: v1.0.0-rc.31...v1.0.0-rc.32

下载资源


v1.0.0-rc.31

正式版本 · 发布于 2026-09-03 21:43:40 (中国时间)

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

New Features

  • Expanded request, response, and streaming conversion across OpenAI Chat Completions, OpenAI Responses, Claude Messages, and Gemini. Hosted tools, citations, grounding metadata, reasoning intent, and authoritative usage are now preserved more faithfully across supported relay paths (#7137, #7170).
  • Added the Anthropic-compatible POST /v1/messages/count_tokens endpoint and enabled Claude channels to serve Gemini-format clients through protocol conversion.
  • Released RelayKit v0.2.0 with conversion diagnostics and configurable tool-loss policies.
  • Added MiniMax-H3 (Hailuo-03) /v2 video generation to the Hailuo task plugin, including multimodal image, video, and audio references, 768P/2K output, and validated 4–15 second durations (#7168, #7171).
  • Added MiniMax-H3 usage facts for input_images and input_video_seconds. Existing ModelBillingExpr values are not migrated automatically and must reference these fields to include input-media charges.

Reliability Improvements

  • Hardened asynchronous task polling with host-level HTTP classification. Upstream 404/410 responses now fail and refund immediately, while transient, authentication, hook, and unrecognized-response failures use a bounded consecutive-failure counter.
  • Added TASK_POLL_MAX_FAILURES, defaulting to 20. A successful poll resets the counter; reaching the limit fails and refunds the task. Set it to 0 or lower to disable this limit. The existing TASK_TIMEOUT_MINUTES deadline remains unchanged.
  • Reduced unnecessary anonymous cold-start authentication requests and added ETag/304 revalidation for public notice, home, about, and legal-content APIs (#7166).
  • Fixed unchanged system-task state writes being incorrectly treated as task-lock loss (#7135).

Billing, Privacy, and Bug Fixes

  • Improved billing integrity across converted and streamed requests by preserving authoritative upstream usage and fixing Claude cache accounting, Gemini modality usage, tool-call surcharges, and interrupted-stream settlement (#7137, #7170).
  • Fixed MiniMax-H3 input-media accounting so bounded estimates can be settled against valid upstream image and duration usage (#7171).
  • Hardened usage-log privacy by separating user, administrator, root, and audit metadata and stripping sensitive channel and rejection details from user-visible log responses.
  • Corrected Video API links across localized documentation (#7116).

New Contributors

  • @To3akaRin made their first contribution in #7116.
  • @NebulaMao made their first contribution in #7168.
  • @CreatorEdition made their first contribution in #7166.

Full Changelog: v1.0.0-rc.30...v1.0.0-rc.31

下载资源


v1.0.0-rc.30

正式版本 · 发布于 2026-08-31 11:55:59 (中国时间)

[!CAUTION] Critical Upgrade Notice / 关键升级提示

v1.0.0-rc.28 和 v1.0.0-rc.29 存在数据库迁移兼容性问题,部分使用 MySQL 或 PostgreSQL 的现有实例在升级后可能无法启动。

  • v1.0.0-rc.29 无法启动或陷入重启循环:请升级至 v1.0.0-rc.30 并重启服务。

v1.0.0-rc.28 and v1.0.0-rc.29 contained a database migration compatibility regression that could prevent some existing MySQL or PostgreSQL deployments from starting after an upgrade.

  • v1.0.0-rc.29 fails to start or enters a restart loop: upgrade to v1.0.0-rc.30 and restart the service.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

Bug Fixes

  • Fixed usage-log statistics showing a zero quota total despite matching consumption records containing non-zero quota. This was a reporting-only issue; consumption logs, actual billing, and account balances were not affected (#7106, #7108).
  • Added a safe and idempotent PostgreSQL migration for known legacy unique constraints on tokens.key, preserving existing token data and key uniqueness while preventing startup migration conflicts.

New Contributors

  • @jimmyleocn made their first contribution in #7108.

Full Changelog: v1.0.0-rc.29...v1.0.0-rc.30

下载资源


v1.0.0-rc.29

正式版本 · 发布于 2026-08-30 23:17:22 (中国时间)

[!CAUTION] Critical Upgrade Notice / 关键升级提示

v1.0.0-rc.28 存在数据库迁移兼容性问题,部分使用 MySQL 或 PostgreSQL 的现有实例在升级后可能无法启动。

  • 仍在 v1.0.0-rc.27:请跳过 v1.0.0-rc.28,直接升级至 v1.0.0-rc.29。

v1.0.0-rc.28 contained a database migration compatibility regression that could prevent some existing MySQL or PostgreSQL deployments from starting after an upgrade.

  • Still on v1.0.0-rc.27: skip v1.0.0-rc.28 and upgrade directly to v1.0.0-rc.29.

[!WARNING] Experimental Plugin System / 实验性插件系统

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。

从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.

Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.

Bug Fixes

  • Fixed database initialization failures on existing MySQL and PostgreSQL deployments caused by incompatible GORM core and database driver versions in v1.0.0-rc.28 (#7098, #7099).
  • Added a safe and idempotent PostgreSQL migration for legacy prefill_groups.name uniqueness constraints, preserving existing data and the intended soft-delete behavior.

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.28...v1.0.0-rc.29

下载资源


v1.0.0-rc.28

正式版本 · 发布于 2026-08-30 21:39:25 (中国时间)

⚠️ IMPORTANT WARNING / 重要警告 ⚠️

自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段,并涉及较大的架构调整。如遇问题,请及时反馈。从 v1.0.0-rc.26 或更早版本升级的用户,必须重新配置所有视频模型价格;已在 v1.0.0-rc.27 完成配置的用户无需重复操作。不推荐在生产环境中使用本版本。

The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly. Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices; users who already completed this step on v1.0.0-rc.27 do not need to repeat it. This release is not recommended for production use.

New Features

  • Added optional RSA-OAEP encryption for password-login request bodies. Enable it with PASSWORD_LOGIN_ENCRYPTION_ENABLED=true; this is an additional safeguard and does not replace HTTPS (#6743).
  • Added AQBot to the default list of third-party chat options (#7079).
  • Added support for channel model-mapping aliases and model-name case variants in task-plugin routing, including consistent upstream mapping and billing resolution.

Improvements

  • Built-in task plugins now update with new-api releases; Marketplace actions no longer create unintended persistent overrides.
  • Improved concurrent-write reliability for the default SQLite configuration by enabling WAL, a 30-second busy timeout, and immediate transactions (#7030).
  • Improved PostgreSQL transaction-pooler compatibility by disabling prepared statements, and fixed JSON-column handling under the simple protocol.

Bug Fixes

  • Prevented unbounded memory retention and potential OOM when an upstream does not return response headers (#6949). RELAY_RESPONSE_HEADER_TIMEOUT now defaults to 1800 seconds; set it to 0 to restore the previous unbounded behavior. Streaming after response headers arrive is unaffected.
  • Fixed the frontend display of the "subscription-only" preference when no valid subscription exists (#7086).
  • Fixed setup-status detection after a page reload (#6968).
  • Changed relay request-validation failures to return HTTP 400 (#6774).
  • Fixed Ali image models to honor the requested response format (#7048).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.27...v1.0.0-rc.28

下载资源


v1.0.0-rc.27

正式版本 · 发布于 2026-08-29 18:55:59 (中国时间)

⚠️ IMPORTANT WARNING / 重要警告 ⚠️

最新版已增加插件系统测试版本,系统架构大改,有bug请立即报告。对于切换到这个版本的用户,需要重新配置所有的视频模型价格!不推荐生产环境使用。

The latest version introduces an experimental plugin system with major architectural changes. Please report any bugs immediately. Users switching to this version MUST reconfigure all video model prices! Not recommended for production environments.

New Features

  • Replaced built-in task adaptors with a new sandboxed JavaScript plugin system (#7076)
  • Added support for GLM channel /v1/responses endpoint (#7050)
  • Enabled passthrough of Claude Messages and OpenAI Responses for Ollama (#7051)

Bug Fixes

  • Fixed an issue in billing where a constantly true time rule expression caused multipliers to apply all day (#6934)
  • Restored the ability for administrators to unbind built-in providers in the web interface (#6987)
  • Fixed docker development build context by adding relaykit go.mod (#7072)

Other

  • Updated PR templates and removed the PR Check workflow (#7053)

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.26...v1.0.0-rc.27

下载资源


v1.0.0-rc.26

正式版本 · 发布于 2026-08-26 21:10:03 (中国时间)

⚠️ Important Warnings / 重要警告

  • Database Migration Risk / 数据库迁移风险: This release changes quota fields to support values larger than 4,294,967,295. Upon startup, the system will check database table structures. Startup may fail if the column types are incorrect. In such cases, manual modification is required (instructions will be in the error message; consult AI if unsure how to proceed). 本次更新修复了额度上限问题,支持大于 42 亿的数值。启动时系统会检测数据库表结构,如果不匹配可能会导致启动失败。遇到此问题需根据错误提示手动修改数据库表结构(如不熟悉数据库操作,可寻求 AI 辅助)。

  • Deprecation of 32-bit Systems / 废弃 32 位系统支持: Support for 32-bit operating systems has been temporarily deprecated to accommodate these changes. 为配合上述更改,我们已“临时”废弃对 32 位操作系统架构的支持。

New Features

  • Added support for thinking_token_budget in vLLM (#7027)

Bug Fixes

  • Prevented browser auto-fill from incorrectly populating credentials in usage log filters (#6966)

Improvements

  • Removed 32-bit integer limitations to allow quota values to exceed 4294 million (#7025)

What's Changed

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.25...v1.0.0-rc.26

下载资源


v1.0.0-rc.25

正式版本 · 发布于 2026-08-18 18:58:54 (中国时间)

Highlights

Channel testing and gateway administration gain safer workflows, user/group-aware overrides, and request-field passthrough controls. This release also improves provider compatibility, Responses API accounting, and recharge/quota reliability.

New Features

  • Channel testing has been expanded with safer test workflows, including an auto-disable-only mode for failing channels (#6917).
  • Parameter overrides can now use requester user and group context for more flexible routing and policy rules (#6534).
  • Gateway channels now let administrators choose which request fields are passed through to upstream providers (#6847).

Bug Fixes

  • Ali provider requests now avoid sending unset top_p values and correctly handle mapped image models (#6772).
  • Qwen TTS models are now classified correctly so they route through the proper text-to-speech path (#6711).
  • Responses API handling now preserves penalties and prompt-cache settings while settling cached-token usage accurately (#6892).
  • Ollama and Claude conversions now preserve reasoning/tool-call context while avoiding invalid empty tool payloads (#6862).
  • Gemini-style model listing requests to /v1/models now return correctly (#6199).
  • Recharge, refund, and quota updates are now settled more consistently, including concurrent and uncreditable order cases (#6845).
  • Web forms now keep fetched model selections in sync, and the mobile sidebar behaves correctly (#6841).
  • Usage logs now record reasoning effort consistently (#6641).
  • Request length validation is now enforced consistently on the backend (#5548).

Improvements

  • Billing logs now highlight the conditional multiplier that matched a request, making cost calculations easier to audit (#6561).
  • Large server and model-list searches in the web UI are debounced, improving responsiveness on big installations (#6727).
  • The playground now displays streamed output with smoother word fade-ins and a more robust editor experience (#6895).
  • Custom channel route editing now has a more capable advanced editor (#6865).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.24...v1.0.0-rc.25

下载资源


v1.0.0-rc.24

正式版本 · 发布于 2026-08-07 17:47:48 (中国时间)

Release: v1.0.0-rc.24

New Features

  • Added user critical rate limiting middleware for access token and affiliate transfer routes to enhance security and stability.
  • Refined the categorization of fetched models in channels to improve organization and retrieval.

Bug Fixes

  • Resolved an issue with redemption code quotas experiencing precision loss, ensuring accurate credit allocation (#6685).
  • Addressed an HTTP/2 transport issue where upstream stream resets could prevent transparent retries by correctly setting Request.GetBody in the relay (#6249).
  • Ensured Claude and Gemini endpoints are tested with the native request format for improved compatibility.

Other

  • Enhanced the release synchronization workflow with optional file syncing capabilities in CI.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.23...v1.0.0-rc.24

下载资源


v1.0.0-rc.23

正式版本 · 发布于 2026-08-01 23:25:04 (中国时间)

Highlights: This release expands provider and channel compatibility with New API channels, DeepSeek Responses API support, zstd request decompression, and automatic group routing. It also improves operational accuracy with stream visibility in logs, more reliable tiered-retry billing, and upstream Bedrock cancellation when clients disconnect.

New Features

  • Added New API channel support with Gemini-to-OpenAI streaming conversion, Advanced Custom Responses Compact handling, and multipart image edit support (#6559).
  • Added DeepSeek Responses API support (#6562).
  • Added automatic group selection for request routing (#6590).
  • Added per-channel HTTP transport controls so administrators can tune connection behavior per channel.
  • Added support for zstd-compressed requests (#6545).
  • Log owners can now see whether a request was streamed (#6558).

Bug Fixes

  • Qwen thinking_budget is now preserved when requests are relayed (#5836).
  • Tiered retry billing now settles usage against the final selected group, including group-switch retries (#6570).
  • Bedrock requests are now cancelled when clients disconnect, reducing wasted upstream work (#6589).

Improvements

  • Public header navigation links now use a consistent font size (#6557).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.22...v1.0.0-rc.23

下载资源


v1.0.0-rc.22

正式版本 · 发布于 2026-07-26 21:19:04 (中国时间)

This release expands channel and model administration with upstream model discovery, new Gemini image models, configurable billing options, and Sub2API support. It also improves reliability across streaming, pricing, refunds, user management, and admin UI workflows.

New Features

  • Channels can now discover available models from advanced custom and Codex-compatible upstreams (#6184).
  • Added support for the latest Gemini image GA models (#6371).
  • Added configurable tool pricing with Sub2API channel support and alpha-search billing.
  • OpenAI Realtime GA models are now available with improved routing compatibility (#6032).

Bug Fixes

  • Responses-to-Chat streaming no longer emits duplicate tool calls (#6225).
  • Creating a model with an existing name no longer clears its saved pricing (#6365).
  • The unset-price models view now lists only models available from the selected channels (#6126).
  • Very large user quota values are now handled without overflow (#6134).
  • User list sorting now works correctly with paginated results (#6194).
  • MiniMax models are now correctly associated with the MiniMax vendor (#6164).
  • Playground model group selectors now handle auto-group listings and long options correctly (#6163).
  • Task refunds are no longer duplicated during concurrent status updates (#6074).
  • Top-up amount fields can now be cleared completely while editing (#6473).
  • Channel inline priority updates are more reliable (#6415).

Improvements

  • Admin JSON editing now has a more consistent experience and avoids UI issues that could hide content (#6421).
  • Users page search is debounced to reduce unnecessary requests and improve responsiveness (#6474).
  • Proxy-backed channel requests are more compatible and stable (#6157).
  • Upstream error logs now provide more useful fallback details when providers return unclear errors (#6431).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.21...v1.0.0-rc.22

下载资源


这篇文档对您有帮助吗?

最后更新于

目录

v1.0.0-rc.51
中文
English
What's Changed
v1.0.0-rc.50
中文
English
What's Changed
New Contributors
v1.0.0-rc.49
中文
English
What's Changed
New Contributors
v1.0.0-rc.48
中文
English
What's Changed
New Contributors
v1.0.0-rc.47
中文
English
What's Changed
New Contributors
v1.0.0-rc.46
中文
English
What's Changed
New Contributors
v1.0.0-rc.45
中文
English
What's Changed
New Contributors
v1.0.0-rc.44
New Features
Fixes and Improvements
What's Changed
New Contributors
v1.0.0-rc.43
New Features
Fixes and Improvements
What's Changed
v1.0.0-rc.42
New Features
Fixes and Improvements
What's Changed
New Contributors
v1.0.0-rc.41
New Features
Fixes and Improvements
What's Changed
New Contributors
v1.0.0-rc.40
New Features
Fixes and Improvements
What's Changed
v1.0.0-rc.39 - Task Plugins & Quota Settings
New Features
Fixes and Improvements
What's Changed
New Contributors
v1.0.0-rc.38 — Responses WebSocket & Request Policies
New Features
Fixes and Improvements
What's Changed
New Contributors
v1.0.0-rc.37- Pricing Configuration, Task Plugins, and Passkey
New Features
Fixes and Improvements
What's Changed
New Contributors
v1.0.0-rc.36 - Task Plugins, Pricing Configuration, and Quota
New Features
Fixes and Improvements
v1.0.0-rc.35 — Wan 3.0 Video, Plugin Routing
New Features
Fixes and Improvements
v1.0.0-rc.34
New Features
Security
Fixes and Improvements
v1.0.0-rc.33
New Features
Billing and Routing
Fixes and Improvements
v1.0.0-rc.32
New Features
Billing and Routing
Relay Improvements
Bug Fixes
v1.0.0-rc.31
New Features
Reliability Improvements
Billing, Privacy, and Bug Fixes
New Contributors
v1.0.0-rc.30
Bug Fixes
New Contributors
v1.0.0-rc.29
Bug Fixes
v1.0.0-rc.28
⚠️ IMPORTANT WARNING / 重要警告 ⚠️
New Features
Improvements
Bug Fixes
What's Changed
New Contributors
v1.0.0-rc.27
⚠️ IMPORTANT WARNING / 重要警告 ⚠️
New Features
Bug Fixes
Other
What's Changed
New Contributors
v1.0.0-rc.26
⚠️ Important Warnings / 重要警告
New Features
Bug Fixes
Improvements
What's Changed
v1.0.0-rc.25
Highlights
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.24
Release: v1.0.0-rc.24
New Features
Bug Fixes
Other
What's Changed
New Contributors
v1.0.0-rc.23
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.22
New Features
Bug Fixes
Improvements
What's Changed
New Contributors