NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
Go modules, #27 by repository stars
Latest stable
v0.13.2
Last release today
17 Nov 2026
Ships on a steady schedule
a new release about every 8 days
No release notes found
nothing matched a version
Nothing withdrawn
no release was ever pulled
1 years old
647 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
Important Account Security / 账户安全功能完善
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.
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.has_password from the existing SELECT without extra queries.telegram slug.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).RawMessage fields to reduce request deep-copy cost (#7221).Full Changelog: v1.0.0-rc.33...v1.0.0-rc.34
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Warning Experimental Plugin System / 实验性插件系统
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.
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.@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>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.base@effort:high@thinking:on and base@thinking:on, with fallback to the base model when no matching variant price is configured.temperature, and topp do not create separate canonical pricing variants.max and xhigh now remain distinct through OpenAI Chat and Responses conversion paths.qwen-max and kimi-k2-thinking.Full Changelog: v1.0.0-rc.31...v1.0.0-rc.33
Warning Experimental Plugin System / 实验性插件系统
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.
@thinking:on, @thinking:off, @thinking:adaptive, or @thinking:<budget>@effort:none|minimal|low|medium|high|xhigh|max@temperature:<number> and @topp:<number>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.base@effort:high@thinking:on or base@thinking:on, with automatic fallback to the base model.temperature and topp never affect the selected billing identity.-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.Full Changelog: v1.0.0-rc.31...v1.0.0-rc.32
Warning Experimental Plugin System / 实验性插件系统
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.
POST /v1/messages/count_tokens endpoint and enabled Claude channels to serve Gemini-format clients through protocol conversion./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).input_images and input_video_seconds. Existing ModelBillingExpr values are not migrated automatically and must reference these fields to include input-media charges.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.Full Changelog: v1.0.0-rc.30...v1.0.0-rc.31
Caution Critical Upgrade Notice / 关键升级提示
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.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.
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.
tokens.key, preserving existing token data and key uniqueness while preventing startup migration conflicts.Full Changelog: v1.0.0-rc.29...v1.0.0-rc.30
Caution Critical Upgrade Notice / 关键升级提示
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。
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.
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.
prefill_groups.name uniqueness constraints, preserving existing data and the intended soft-delete behavior.Full Changelog: v1.0.0-rc.28...v1.0.0-rc.29
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。
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.
PASSWORD_LOGIN_ENCRYPTION_ENABLED=true; this is an additional safeguard and does not replace HTTPS (#6743).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.Full Changelog: v1.0.0-rc.27...v1.0.0-rc.28
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 。
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.
/v1/responses endpoint (#7050)Full Changelog: v1.0.0-rc.26...v1.0.0-rc.27
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…
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。
thinking_token_budget in vLLM (#7027)Full Changelog: v1.0.0-rc.25...v1.0.0-rc.26
Channel testing and gateway administration gain safer workflows, user/group-aware overrides, and request-field passthrough controls. This release also
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.
top_p values and correctly handle mapped image models (#6772)./v1/models now return correctly (#6199).Full Changelog: v1.0.0-rc.24...v1.0.0-rc.25
Added user critical rate limiting middleware for access token and affiliate transfer routes to enhance security and stability.
Request.GetBody in the relay (#6249).Full Changelog: v1.0.0-rc.23...v1.0.0-rc.24
Highlights: This release expands provider and channel compatibility with New API channels, DeepSeek Responses API support, zstd request decompression,
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.
thinking_budget is now preserved when requests are relayed (#5836).Full Changelog: v1.0.0-rc.22...v1.0.0-rc.23
This release expands channel and model administration with upstream model discovery, new Gemini image models, configurable billing options, and Sub2AP
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.
Full Changelog: v1.0.0-rc.21...v1.0.0-rc.22
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 a
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.
cache_write_tokens at the cache-creation rate while keeping cached and uncached prompt token accounting consistent.Full Changelog: v1.0.0-rc.20...v1.0.0-rc.21
This release adds GPT-5.6 pricing support and stale instance cleanup tools for administrators. It also fixes several quota and pricing edge cases, inc
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.
0.05 to be typed normally. (#5995)Full Changelog: v1.0.0-rc.19-i18nfix.2...v1.0.0-rc.20
Admins can now reset subscription quotas and review quota saturation events for auditing, making quota management easier ( #5952 ).
Full Changelog: v1.0.0-rc.18...v1.0.0-rc.19
Nothing published for this version
v1.0.0-rc.18 Compare # Choose a tag to compare
v1.0.0-rc.18
Compare
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.