Releases: QuantumNous/new-api
Releases · QuantumNous/new-api
v0.8.7.1
What's Changed
- feat: 优化分页组件 by @xiangyuanliu in #1298
- fix: ratelimit style error by @tbphp in #1301
- feat: jimeng apiKey format to use
|
delimiter by @feitianbubu in #1322
New Contributors
- @xiangyuanliu made their first contribution in #1298
Full Changelog: v0.8.7.0...v0.8.7.1
v0.8.7.0
What's Changed
- feat: add origin kling api by @feitianbubu in #1291
- feat: 支持即梦视频渠道 by @feitianbubu in #1274
Full Changelog: v0.8.6.3...v0.8.7.0
v0.8.6.3
What's Changed
- Feat copy models 新增功能:复制所有模型 by @JoeyLearnsToCode in #1290
Full Changelog: v0.8.6.2...v0.8.6.3
v0.8.6.2
What's Changed
- feat: add placeholder for kling AccessKey and SecretKey by @feitianbubu in #1279
- feat: openrouter format for claude request by @prnake in #1235
- feat: enhance token usage details for upstream OpenRouter by @neotf in #1120
- feat: support user-group-specific for mj and task by @creamlike1024 in #1281
Full Changelog: v0.8.6.1...v0.8.6.2
v0.8.6.1
What's Changed
- feat(model-ratio): add default ratios for new Gemini models and refine flash model handling by @RedwindA in #1248
- feat: allow for a lower percentage of the thinkingBudget by @RedwindA in #1210
- refactor: optimize Dockerfile apk usage by @PeterDaveHello in #1135
- feat: add moonshot(kimi) update balance by @feitianbubu in #1160
- Feat_火山引擎文生图 by @bddiudiu in #1095
- feat: conditionally set Gemini ThinkingBudget based on MaxOutputTokens by @Calcium-Ion in #1278
New Contributors
- @PeterDaveHello made their first contribution in #1135
- @bddiudiu made their first contribution in #1095
Full Changelog: v0.8.6.0...v0.8.6.1
v0.8.6.0
What's Changed
- feat: 支持可灵视频渠道(异步任务) by @feitianbubu in #1244
- feat: implement new handlers for relay processing by @Calcium-Ion in #1270
- 🔄 feat(ratio-sync): introduce upstream ratio synchronisation feature #1220 by @t0ng7u in #1267
- feat: vertex budget control in model name by @RedwindA in #1271
- fix: gemini 原生格式流模式中断请求未计费 by @creamlike1024 in #1272
- fix: unique channel models by @feitianbubu in #1264
- fix: playground write user context to check acceptUnsetRatio by @feitianbubu in #1252
Full Changelog: v0.8.5.2...v0.8.5.3
v0.8.5.2
What's Changed
- fix: gemini relay empty response by @Calcium-Ion in #1268
Full Changelog: v0.8.5.1...v0.8.5.2
v0.8.5.1
What's Changed
- fix: task cost time by @feitianbubu in #1258
- feat: 自定义充值方式 by @creamlike1024 in #1257
- fix: 修复渠道界面模型选择下拉框模型重复显示 by @wans10 in #1262
- feat: 透传thinking参数, 豆包模型用来控制是否思考 by @KamiPasi in #1261
- fix: Gemini & Vertex empty content error by @tbphp in #1260
- Fix Vertex channel global region format for claude models by @sgyy in #1253
- fix: gemini原生格式请求,非流情况下,不计算reasoning_tokens by @xqx121 in #1254
New Contributors
- @wans10 made their first contribution in #1262
- @KamiPasi made their first contribution in #1261
- @sgyy made their first contribution in #1253
Full Changelog: v0.8.5.0...v0.8.5.1
v0.8.5.0
What's Changed
- feat: auto分组 by @creamlike1024 in #1239
- feat: improve gemini thinking budget adaption by @RedwindA in #1247
auto分组使用教程
将依次从自动分组的第一位开始选择分组,如果该分组请求失败,则顺位到下一个分组请求,适用于需要一个令牌访问所有模型的用户
扣费将使用选择的分组倍率进行扣费
Full Changelog: v0.8.4.2...v0.8.5.0
v0.8.4.2
What's Changed
- 修复Azure渠道对responses API的兼容性支持 - 为Azure渠道添加对responses API的特殊处理 - 兼容微软新… by @a37836323 in #1205
- fix: enabled hot reload SyncOptions by @feitianbubu in #1208
- feat(Gemini): implement thinking budget control in model name by @RedwindA in #1231
- Fix: optimize Redis expiration handling and refactor cache duration retrieval by @RedwindA in #1240
- fix(audio): :bugs: fix webm audio strconv.ParseFloat: parsing "N/A" by @cjm0810151 in #1243
New Contributors
- @cjm0810151 made their first contribution in #1243
Full Changelog: v0.8.4.1...v0.8.4.2