v0.12.14

Improvements

• Improved user-visible management and top-up logs with a cleaner display, preserved row expansion, and clearer handling of legacy records.

---

Full Changelog: v0.12.13...v0.12.14

v0.12.13

This release improves admin workflows for top-ups and makes account status changes apply more consistently.

Bug Fixes

• Disabling a user now takes effect immediately instead of being delayed by stale cached account data.

Improvements

• Top-up logs now include additional admin-only audit details to make review and troubleshooting easier.

Breaking Changes

• Top-up searches are now limited to a maximum 30-day date range to keep queries responsive and reliable.

---

Full Changelog: v0.12.12...v0.12.13

v0.12.12

This release adds support for Claude Opus 4.7, expanding the set of available models in the API.

New Features

• Added support for the Claude Opus 4.7 model, making it available through the API alongside existing model options (#4293).

---

What's Changed

• feat: support claude-opus-4-7 by @prnake in #4293
• chore(deps): bump github.com/jackc/pgx/v5 from 5.7.1 to 5.9.0 by @dependabot[bot] in #4294

Full Changelog: v0.12.11...v0.12.12

v0.12.11

New Features

• Added payment method tracking and validation for top-ups.

Bug Fixes

• Improved handling of empty string content during OpenAI to Claude message conversion.

---

Full Changelog: v0.12.10...v0.12.11

v0.12.10

New Features

• Added passthrough support for Claude cache_control and speed options, giving you more control over request behavior when using Claude models (#4247).

Bug Fixes

• Fixed OpenAI Responses API compatibility issues when instructions contain structured content instead of plain text (#4260).

Improvements

• Improved Stripe payment processing to better handle asynchronous webhook events, making delayed payment confirmations more reliable.
• Quota adjustment logs now record the acting admin username, making administrative audit trails easier to follow (#4216).

---

What's Changed

• fix: use json.RawMessage for Instructions field in OpenAIResponsesResponse by @linbin524 in #4260
• fix(channel): 修复多密钥管理弹窗索引显示，将索引值调整为从1开始 by @wans10 in #4231
• feat(claude): add cache_control and speed passthrough controls by @seefs001 in #4247
• feat: include admin username in quota adjustment logs by @feitianbubu in #4216

New Contributors

• @linbin524 made their first contribution in #4260

Full Changelog: v0.12.9...v0.12.10

v0.12.9

New Features

• Subscription cards now show the next quota reset time, making it easier to see when usage limits will refresh (#4181).

Bug Fixes

• Claude requests are now more reliable by avoiding incompatible Top P settings when needed.
• Azure channels now correctly support the /v1/responses/compact route (#4149).
• Editing values in GroupTable no longer forces the cursor to jump to the end on each keystroke (#4208).

Improvements

• Dashboard charts have been refined to present rankings and chart sizing more clearly for easier monitoring.

---

What's Changed

• fix(GroupTable): prevent Input cursor jumping to end on keystroke by @Xbang0222 in #4208
• feat: display next quota reset time in subscription card by @ShengM97 in #4181
• fix: add Azure channel support for /v1/responses/compact URL routing by @woan1136 in #4149

New Contributors

• @Xbang0222 made their first contribution in #4208
• @ShengM97 made their first contribution in #4181
• @woan1136 made their first contribution in #4149

Full Changelog: v0.12.8...v0.12.9

v0.12.8

Bug Fixes

• Correctly report the stream status in error logs instead of defaulting to false (#4195).

---

What's Changed

• fix: isStream status in error logs instead of hardcoded false by @feitianbubu in #4195
• chore(deps): bump axios from 1.13.5 to 1.15.0 in /web by @dependabot[bot] in #4201

Full Changelog: v0.12.7...v0.12.8

v0.12.7

Improvements

• Quota management now uses an amount-first input flow and applies changes atomically, making balance adjustments simpler and more reliable.
• Model pricing errors now use cleaner, role-aware messages so it is easier to understand and resolve failed pricing actions.

---

Full Changelog: v0.12.6...v0.12.7

v0.12.6

New Features

• Fill in custom fields for vllm-omini (#4154)

Bug Fixes

• Accept string usage values in Alibaba task polling (#4155)
• Use correct endpoint for coding plan image generation in Zhipu 4V (#4146)
• Prefer explicit pricing for compact models (#4156)
• Fix document rendering (#4153)

Improvements

• Refine PR template and add PR submission checks (#4076)

---

What's Changed

• fix(zhipu_4v): use correct endpoint for coding plan image generation by @NyaMisty in #4146
• fix: prefer explicit pricing for compact models by @seefs001 in #4156
• fix(ali): accept string usage values in task polling by @seefs001 in #4155
• feat: fill in some custom fields for vllm-omini by @seefs001 in #4154
• fix: document render by @seefs001 in #4153
• ci: refine PR template and add PR submission checks by @seefs001 in #4076

New Contributors

• @NyaMisty made their first contribution in #4146

Full Changelog: v0.12.5...v0.12.6

nightly-20260409-4d2993e

Highlights / 重点更新

This release introduces comprehensive support for tiered billing (阶梯计费). It allows for flexible pricing expressions, detailed tool call quota calculations, and channel test support for tiered models.
本次发布重点增加了对阶梯计费的全面支持，支持灵活的计费表达式解析、自定义工具调用额度计算，并完善了UI配置项和渠道测试支持。

Docker image: calciumion/new-api:nightly
Docker 镜像: calciumion/new-api:nightly

New Features

• Added comprehensive support for tiered billing, including flexible expression evaluation, tool pricing settings UI, and channel test support (#4145).
• Added custom fields support for vllm-omini models (#4154).

Bug Fixes

• Fixed an issue in Alibaba Cloud task polling to correctly accept string usage values (#4155).
• Fixed the endpoint for Zhipu 4v coding plan image generation (#4146).
• Fixed pricing calculation to prefer explicit pricing for compact models (#4156).

Improvements

• Improved UI layout consistency by replacing card components with divs.
• Added nightly branch trigger to Docker image CI workflows.
• Refined PR templates and added PR submission checks (#4076).

---

What's Changed

• fix(zhipu_4v): use correct endpoint for coding plan image generation by @NyaMisty in #4146
• fix: prefer explicit pricing for compact models by @seefs001 in #4156
• fix(ali): accept string usage values in task polling by @seefs001 in #4155
• feat: fill in some custom fields for vllm-omini by @seefs001 in #4154
• fix: document render by @seefs001 in #4153
• ci: refine PR template and add PR submission checks by @seefs001 in #4076
• fix(channel-test): support tiered billing model tests by @yyhhyyyyyy in #4145

New Contributors

• @NyaMisty made their first contribution in #4146

Full Changelog: v0.12.5...nightly-20260409