New APINew API
User GuideInstallationAPI ReferenceAI ApplicationsSkillsHelp & SupportBusiness Cooperation

Changelog

Version Log Information · Data updated at 2026-9-10 11:04:48

To view all historical versions, please visit the GitHub Releases page. This page automatically fetches the latest update information from that page.

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

Latest Release · Published at 2026-09-08 21:01:52 (UTC+8)

[!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

Download Resources

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

Release · Published at 2026-09-07 22:45:50 (UTC+8)

[!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

Download Resources

v1.0.0-rc.34

Release · Published at 2026-09-06 22:53:49 (UTC+8)

[!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

Download Resources

v1.0.0-rc.33

Release · Published at 2026-09-05 11:54:42 (UTC+8)

[!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

Download Resources

v1.0.0-rc.32

Release · Published at 2026-09-05 00:08:45 (UTC+8)

[!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

Download Resources

v1.0.0-rc.31

Release · Published at 2026-09-03 21:43:40 (UTC+8)

[!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

Download Resources

v1.0.0-rc.30

Release · Published at 2026-08-31 11:55:59 (UTC+8)

[!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

Download Resources

v1.0.0-rc.29

Release · Published at 2026-08-30 23:17:22 (UTC+8)

[!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

Download Resources

v1.0.0-rc.28

Release · Published at 2026-08-30 21:39:25 (UTC+8)

⚠️ 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

Download Resources

v1.0.0-rc.27

Release · Published at 2026-08-29 18:55:59 (UTC+8)

⚠️ 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

Download Resources

v1.0.0-rc.26

Release · Published at 2026-08-26 21:10:03 (UTC+8)

⚠️ 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

Download Resources

v1.0.0-rc.25

Release · Published at 2026-08-18 18:58:54 (UTC+8)

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

Download Resources

v1.0.0-rc.24

Release · Published at 2026-08-07 17:47:48 (UTC+8)

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

Download Resources

v1.0.0-rc.23

Release · Published at 2026-08-01 23:25:04 (UTC+8)

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

Download Resources

v1.0.0-rc.22

Release · Published at 2026-07-26 21:19:04 (UTC+8)

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

Download Resources

v1.0.0-rc.21

Release · Published at 2026-07-11 23:01:26 (UTC+8)

Highlights

The headline change is GPT-5.6 cache write billing: OpenAI cache_write_tokens are now charged at the cache-creation rate, with accounting safeguards around cached and uncached prompt tokens. This release also improves pricing workflows, Playground controls, channel table usability, and billing/logging reliability.

New Features

  • Added GPT-5.6 cache write billing support, charging OpenAI cache_write_tokens at the cache-creation rate while keeping cached and uncached prompt token accounting consistent.
  • Pricing pages now support group-aware dynamic calculations and avoid showing sample-only special groups (#5906).
  • Model pricing settings now include an Unset Price Models tab plus status and sync filters, making it easier to find and configure models without prices (#6124).
  • The Playground now includes request parameter panels for chat and generation tuning, so users can adjust model behavior directly in the UI (#6044).
  • Channel lists now support manual column resizing and keep resized tables filling the available width (#5948).
  • Logs now show stream timing metrics and task detail views for clearer troubleshooting.
  • Added enhanced text protocol conversion and advanced custom routing capabilities for more flexible channel routing (#5825).

Bug Fixes

  • Browser translation can no longer corrupt React-rendered pages (#5963).
  • Custom model names that differ only by case can now be added consistently, including from multi-select controls (#6061).
  • Billing now handles quota pre-consumption and image-stream disconnect edge cases more accurately.
  • Subscription reset handling is more reliable under concurrent updates (#6057).
  • Codex response passthrough fields now sync correctly (#6018).
  • Playground model selector lists now stay synchronized after model changes.
  • Custom home iframes can trigger top navigation after a user action as intended (#5955).
  • Restored paste behavior for default channel connection settings.

Improvements

  • Upstream price sync tables in model pricing now load and render more efficiently (#6092).
  • Refined table badges, pricing layouts, sync dialogs, and default theme styling for a cleaner admin UI.
  • Font assets now resolve correctly across workspace layouts.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.20...v1.0.0-rc.21

Download Resources

v1.0.0-rc.20

Release · Published at 2026-07-07 21:46:39 (UTC+8)

Highlights

This release adds GPT-5.6 pricing support and stale instance cleanup tools for administrators. It also fixes several quota and pricing edge cases, including wallet reward transfers and decimal ratio input.

New Features

  • Added token pricing support for GPT-5.6 models.
  • Added system-info actions for cleaning up stale instances. (#5953)

Bug Fixes

  • Wallet reward transfers now respect the configured quota unit instead of using an incorrect fixed unit. (#5808)
  • Group ratio fields now allow decimal values such as 0.05 to be typed normally. (#5995)
  • Tiered pricing now uses a default token estimate during pre-consumption, improving quota calculation for affected pricing rules.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.19-i18nfix.2...v1.0.0-rc.20

Download Resources

v1.0.0-rc.19-i18nfix.2

Release · Published at 2026-07-07 14:06:07 (UTC+8)

Fix i18n error

Download Resources

v1.0.0-rc.19

Release · Published at 2026-07-07 13:19:27 (UTC+8)

New Features

  • Admins can now reset subscription quotas and review quota saturation events for auditing, making quota management easier (#5952).
  • Added Traditional Chinese (zh-TW) localization for the new UI (#5942).

Bug Fixes

  • Fixed billing quota calculations for very large quotas so limits are applied correctly.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.18...v1.0.0-rc.19

Download Resources

v1.0.0-rc.18

Release · Published at 2026-07-07 01:16:57 (UTC+8)

Billing quota handling is more reliable in this release, with stricter quantity validation to prevent incorrect quota calculations.

Bug Fixes

  • Improved billing quantity validation so quota and usage calculations handle invalid or extreme values more reliably.

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.17...v1.0.0-rc.18

Download Resources

v1.0.0-rc.17

Release · Published at 2026-07-06 22:37:46 (UTC+8)

Highlights

This release improves channel testing, redemption management, theme handling, and several web UI flows. It also fixes usage reporting, classic web builds, streaming disconnect handling, and quota/video duration calculations.

New Features

  • Redemption management now supports status filtering and cleanup actions for easier administration.
  • Group ratio editing is easier to use, with clearer visibility behavior and more robust JSON input handling.
  • Redeem failures now show clearer messages so users can understand what went wrong.

Bug Fixes

  • AI Elements integrations now read nested usage data so token usage is reported correctly.
  • Classic web builds now complete successfully again (#5892).
  • Field passthrough controls now appear correctly for Codex channels (#5902).
  • Home iframes now stay in sync with the selected theme and language (#5917).
  • Custom HTML rendered inside Shadow DOM now follows light and dark mode changes correctly (#5890).
  • Logged-in users are now redirected away from the sign-up page consistently with the login and classic themes (#5910).
  • Streaming responses no longer continue writing after the client disconnects (#5710).
  • Quota settlement and Ali video duration handling were corrected after task balance settlement (#5923).
  • Build date generation no longer fails when DNS lookup fails (#5945).

Improvements

  • Channel and model test dialogs are more compact and easier to operate (#5886).
  • Dynamic pricing details now use styling consistent with the log details dialog (#5905).
  • Mobile user cards have been refined for better readability and layout.
  • Legacy top-up warning text is clearer and easier to understand (#5855).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.16...v1.0.0-rc.17

Download Resources

v1.0.0-rc.16

Release · Published at 2026-07-03 15:41:42 (UTC+8)

Highlights

This release expands model and media compatibility with Responses/Chat interoperability, Doubao Seedance 2.0 updates, and Wan2.7 i2v media mapping. It also improves the web experience around Playground rendering, channel management, page state retention, and graceful restarts.

New Features

  • Added Responses API to Chat compatibility so providers and clients using either format can interoperate more reliably (#5787).
  • Expanded Doubao Seedance 2.0 support with material asset APIs, resolution-aware billing, video-input billing, 4K billing, and new request options (#5824).
  • Added Wan2.7 image-to-video media mapping support (#4984).
  • Added graceful shutdown support to reduce interrupted replies and avoid losing cached panel data during restarts (#4258).
  • Improved channel management with a clearer layout and a more capable advanced custom route editor.

Bug Fixes

  • Fixed the model pricing tiered expression editor so it refreshes correctly when switching between models (#5752).
  • Fixed async task usage logs so usage is attributed to the node that initiated the task (#5684).
  • Fixed theme switching so the app returns to the home page instead of landing on a 404 route (#5612).
  • Fixed custom HTML and Markdown rendering so content keeps consistent styling and spacing, including isolated HTML views (#5795).
  • Fixed page state resets when switching tabs within the same route, including dashboard time ranges (#5796).
  • Fixed channel status filters so they persist across page navigation (#5863).
  • Fixed Ollama non-streaming tool call handling (#5865).
  • Fixed Waffo product information and webhook behavior (#5704).

Improvements

  • Improved the Playground chat experience and Markdown rendering (#5217).
  • Streamlined table actions and destructive confirmation dialogs for a cleaner web UI (#5645).
  • Improved ClickHouse log filtering for LIKE queries.
  • Optimized the frontend build pipeline for faster web builds (#5786).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.15...v1.0.0-rc.16

Download Resources

v1.0.0-rc.15

Release · Published at 2026-06-24 21:00:04 (UTC+8)

Highlights

This release adds several operations-focused controls, including passive channel monitoring, ClickHouse-backed log storage, system task execution, and instance visibility. It also improves frontend reliability and polish across usage logs, markdown rendering, channel selection, and optional wallet UI behavior.

New Features

  • Added passive channel monitoring mode for checking channel health without actively disrupting traffic (#5592).
  • Added support for storing logs in ClickHouse for deployments that need scalable log storage and querying (#5663).
  • Added a system task runner with persistent cleanup progress tracking for long-running maintenance jobs (#5680).
  • Added a system instance information panel to make deployment/node status easier to inspect (#5716).
  • Added a user token limit configuration section in system settings (#5678).
  • Added channel testing controls for environment selection and asynchronous polling delay configuration.
  • Default node names now fall back to the machine hostname when NODE_NAME is not set (#5659).

Bug Fixes

  • Usage logs now show provider icons correctly for CN models (#5631).
  • Corrected the Stepfun provider display name (#5636).
  • Fixed SMTP compatibility with STARTTLS mode and NTLM authentication (#5426).
  • Fixed classic theme build failures related to timezone date handling (#5676).
  • Improved markdown rendering and expanded syntax support in the web UI (#5689).
  • Fixed channel card selection state so the UI stays in sync with the selected channel (#5700).
  • Hid the wallet entry from the profile dropdown when the wallet module is disabled (#5708).

Improvements

  • Simplified log cleanup behavior as part of the new ClickHouse logging and system task maintenance flow.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.14...v1.0.0-rc.15

Download Resources

v1.0.0-rc.14

Release · Published at 2026-06-20 22:15:42 (UTC+8)

Highlights

This release adds a new dashboard traffic flow Sankey chart for visualizing token routing and flow patterns, with interactive highlighting, persistent filters, and limits to keep large graphs readable. Channel management also gets a faster, cleaner card layout for easier browsing and reduced UI re-rendering.

New Features

  • Added a dashboard traffic flow Sankey chart to help admins understand token flow and routing behavior at a glance (#5465).
  • Added routing reliability management for better control and visibility over routing behavior.
Traffic flow chartChannel management card layout
QQ_1781965314487

Bug Fixes

  • Fixed log filtering by login type in the new frontend (#5620).
  • Fixed the billing history dialog layout so pagination no longer overlaps the list (#5627).
  • Fixed model pricing entries that could not be deleted from the visual pricing list (#5628).
  • Fixed repeated database column migrations running again after restarts (#5361, #5616).

Improvements

  • Improved the channel management card layout and reduced unnecessary re-renders for a smoother experience.
  • Simplified the model list for easier scanning and management.
  • Updated channel icons for better visual consistency.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.13...v1.0.0-rc.14

Download Resources

v1.0.0-rc.13

Release · Published at 2026-06-19 20:28:34 (UTC+8)

v1.0.0-rc.13 focuses on a more polished and responsive frontend experience, especially around channel management and data-heavy pages. The channel page now supports a card-style display with improved mobile layouts, while logs, metrics, endpoint selection, date picking, and usage views received UI/UX refinements.

New Features

  • Added a reusable card/table view toggle for data tables, including a new card layout that makes channel and table-heavy pages easier to browse on different screen sizes.
  • Added locale-aware number formatting so numeric values are displayed more naturally for users in different regions.

Improvements

  • Improved the channel page card layout with a clearer left/right structure and better mobile handling for small screens.
  • Refined logs, metrics, endpoint selection, date picker, toolbar controls, and model drawer interfaces for a cleaner and more consistent UI/UX.
  • Updated the Codex usage interface for better readability and usability (#5595).
  • Reduced unnecessary data refreshes when returning focus to the browser window, improving frontend performance.
  • Updated frontend branding copy and visual styling for a more consistent product experience.

Bug Fixes

  • Improved timestamp precision in drawing-related displays by including milliseconds where needed.

What's Changed

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.12...v1.0.0-rc.13

Download Resources

v1.0.0-rc.12

Release · Published at 2026-06-18 20:34:16 (UTC+8)

Highlights: This release introduces AdvancedCustom channels for more flexible custom routing, makes channel batch testing easier to act on, and expands model marketplace performance monitoring with clearer success-rate and latency insights.

New Features

  • Added AdvancedCustom channels with improved custom route matching for more flexible provider and model routing (#5590).
  • Enhanced channel model batch testing with complete test execution, refreshed status updates, clearer results, failed-model deletion, and copying selected models (#5532).
  • Expanded model marketplace performance monitoring with uptime calculations, recent success rates, success-rate grading, and compact latency/throughput displays.
  • Added persistent table preferences so page size and column visibility are remembered across navigation and sessions (#5403).

Bug Fixes

  • Fixed tool-call handling so empty arguments values still preserve the expected tool_use block (#5543).
  • Fixed the CC Switch model selector so model choices display and update correctly (#5515).
  • Fixed several UI clipping and overflow issues in lists, data tables, usage log details, and custom home iframes (#5510, #5536, #5533, #5545).

Improvements

  • Improved payment and recharge UI with clearer payment method buttons, icons, and minimum top-up information.
  • Improved subscription plan presentation with purchase descriptions, wallet overflow handling, and downgrade group support.
  • Refined settings, overview setup guide, wallet/profile interactions, and log statistic card layouts for better readability.

Breaking Changes

  • Subscription product option and catalog endpoints now use GET, which may require client integrations to update their request method.
  • Removed the “All” period option from rankings filters.

What's Changed

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.11...v1.0.0-rc.12

Download Resources

v1.0.0-rc.11

Release · Published at 2026-06-13 16:15:40 (UTC+8)

Highlights: This release adds support for Claude Opus 4.8, improves OpenAI image API compatibility, and makes the model pricing editor and data-heavy tables easier to use. It also fixes several UI, quota display, relay compatibility, and provider-specific issues.

New Features

  • Added support for Claude Opus 4.8 (#5177).
  • Added an option to control whether channel stickiness is cleared when a channel is disabled (#5306).
  • Added a subscription balance redemption toggle for more flexible balance handling.
  • Added user ID visibility on the profile page (#5317).
  • Added support for streaming image relay and image edits in the OpenAI images API (#4608).

Bug Fixes

  • Forms now focus the first validation error after submission, making errors easier to find and correct (#5163).
  • Fixed custom cc-switch names being reset after losing focus (#5170).
  • Fixed custom model icons not staying in sync in pricing views (#5224).
  • Fixed advanced channel validation errors so they are shown without incorrectly expanding unrelated settings (#5239).
  • Fixed quota and balance displays so currency conversion updates both the unit and the displayed value (#5296).
  • Fixed Dify remote-image handling in file-based requests (#5134).
  • Fixed model resolution for video generation task lookups (#5133).
  • Improved Anthropic-compatible GLM relay behavior to avoid compatibility failures (#5307).
  • Narrowed OpenAI o-series model adaptation to avoid applying it to unsupported models (#5293).
  • Fixed multiselect popovers so they respect the active theme (#5328).
  • Fixed Kimi K2.6 temperature normalization (#5390).
  • Added support for filtering deleted users by status (#5464).
  • Fixed deployment settings loading so they are only fetched on the deployments page (#5466).

Improvements

  • Improved admin log and batch update performance for smoother large-scale operations (#5116).
  • Improved the model pricing editor with clearer layouts, better draft saving, reusable JSON editing, and support for six-decimal pricing steps (#5275).
  • Improved channel search responsiveness with debouncing and better IME input handling (#5393).
  • Improved frontend table rendering, pinned columns, table layout, and badge display (#5405).
  • Improved dialog sizing and footer layout across the frontend (#5346).
  • Simplified public page hero copy for a cleaner landing page (#5339).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.10...v1.0.0-rc.11

Download Resources

v1.0.0-rc.10

Release · Published at 2026-05-26 22:20:13 (UTC+8)

Highlights

v1.0.0-rc.10 focuses on UI polish, relay reliability, and admin workflow fixes. It adds new theme options and subscription balance purchases while tightening logs, channel behavior, webhooks, payments, and provider tool-call handling.

New Features

  • New theme customization options add Anthropic and Simple Large presets, configurable serif typography, and an extra-large scaling option.
  • Subscription billing now supports balance purchases.

Bug Fixes

  • Automatically disabled channels are no longer selected for new requests, and channel actions no longer show duplicate notifications (#4983).
  • Tool-call relays between Gemini and Claude are more reliable, including concurrent tool calls (#5095).
  • Image relay requests now apply the requested quality setting correctly (#5103).
  • Usage log filters now match exact values unless a wildcard is explicitly used, and very large upstream errors are shortened to keep logs usable (#5097).
  • Webhook processing now completes more reliably (#5047).
  • Waffo payment settings now save consistently and hide legacy options (#5110).
  • System Settings now detects unsaved changes correctly and handles numeric inputs without invalid values.

Improvements

  • Large media relay requests now use less memory, improving stability under load.
  • System Settings and channel creation/editing pages have clearer, more compact layouts with improved controls.
  • Usage logs and the default web UI are easier to use on mobile and easier to scan, with better table spacing, badges, charts, and dark-mode readability.
  • The homepage hero section has been refreshed with a cleaner two-column layout and updated copy.

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.8...v1.0.0-rc.10

Download Resources

v1.0.0-rc.8

Release · Published at 2026-05-22 16:25:46 (UTC+8)

Highlights

This release adds Waffo Pancake gateway support with admin catalog/product binding and focuses on polishing admin/API behavior. It also improves model metadata and pricing consistency, channel-test diagnostics, dashboard/reporting filters, and request-processing efficiency.

New Features

  • Added Waffo Pancake gateway support with admin catalog/product binding (#4935).

Bug Fixes

  • Dashboard content now follows configured visibility settings consistently (#4975).
  • Performance metric summaries now include only active groups (#4976).
  • Model pricing displays are now normalized to avoid inconsistent values (#4985).
  • Model ownership metadata is now resolved from active channels for more accurate model listings (#4416).
  • Default frontend links now point to the correct routes (#5016).
  • Restored the previous usage-log filtering behavior to avoid regressions from the earlier filter change.

Improvements

  • Channel tests now show clearer failure details when checks fail (#4988).
  • Reduced request-processing overhead to improve performance under load (#5009).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.7...v1.0.0-rc.8

Download Resources

v1.0.0-rc.7

Release · Published at 2026-05-19 16:54:08 (UTC+8)

New Features

  • Added support for request_header key source (#4903).

Bug Fixes

  • Batch fixed multiple UI issues in the default web interface (#4880, #4893, #4817, #4877, #4898, #4876).
  • Addressed an issue where channel remarks could not be cleared (#4886).
  • Corrected the filtering behavior for usage logs (#4883).
  • Fixed validation for unlimited API key quotas in the web interface (#4881).
  • Enforced access control on header navigation for public modules (#4889).
  • Applied group filters correctly to channel list queries (#4847, #4885).
  • Fixed an ambiguity issue with column names during PerfMetric upserts (#4684).
  • Added missing analytics placeholders to the default theme (#4928).
  • Fixed forgot password form submission by properly typing the button (#4910).
  • Normalized the layout of model detail tabs in the web interface (#4938).
  • Fixed user creation and deletion handling in the management panel (#4818).
  • Gated the sign-up link on the login page based on registration settings (#4871).
  • Updated pagination button labels in the ModelCardGrid (#4675).
  • Localized the reset password confirmation message (#4769).
  • Made recharge preset selections visible in dark mode (#4897).
  • Fixed an issue where the API info color dot showed the wrong color due to a semantic token mismatch (#4824).
  • Corrected silent failures when saving API info with invalid colors (#4823).
  • Used the correct aff_code field name in registration payloads (#4965).
  • Made the faceted filter popover width adaptive in data tables (#4966).
  • Resolved stale form linkage issues when submitting keys (#4967).

Improvements

  • Improved performance by avoiding eager formatting in debug log calls (#4929).

What's Changed

New Contributors

Full Changelog: https://github.com/QuantumNous/new-api/compare/v1.0.0-rc.6...v1.0.0-rc.7

Download Resources

How is this guide?

Last updated on

Performance Analysis Setup Guide

Previous Page

Feature Guide Overview

New API feature guide, organized into User Guide and Admin Guide.

On this page

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
v1.0.0-rc.21
Highlights
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.20
Highlights
New Features
Bug Fixes
What's Changed
New Contributors
v1.0.0-rc.19-i18nfix.2
v1.0.0-rc.19
New Features
Bug Fixes
What's Changed
New Contributors
v1.0.0-rc.18
v1.0.0-rc.17
Highlights
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.16
What's Changed
New Contributors
v1.0.0-rc.15
Highlights
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.14
Highlights
New Features
Gallery
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.13
New Features
Improvements
Bug Fixes
What's Changed
v1.0.0-rc.12
New Features
Bug Fixes
Improvements
Breaking Changes
What's Changed
v1.0.0-rc.11
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.10
Highlights
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.8
Highlights
New Features
Bug Fixes
Improvements
What's Changed
New Contributors
v1.0.0-rc.7
New Features
Bug Fixes
Improvements
What's Changed
New Contributors