 Xyfacai
|
a4bfec164e
fix: 未设置价格模型不会被拉取，除非设置自用模式
|
9 месяцев назад |
 Sh1n3zZ
|
af671d34c3
feat: replicate channel flux model
|
9 месяцев назад |
 Seefs
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 месяцев назад |
|
Xyfacai
|
09495c8ef6
feat: sora 增加参数校验与计费
|
10 месяцев назад |
 creamlike1024
|
eeef719f3a
feat: 支持 gemini-robotics-er-1.5-preview
|
10 месяцев назад |
|
Seefs
|
740c46102b
Merge pull request #1924 from prnake/claude-4-5
|
10 месяцев назад |
 papersnake
|
112ab0b17c
feat: support claude-sonnet-4-5-20250929
|
10 месяцев назад |
 dd
|
f9399e279c
Merge branch 'QuantumNous:main' into main
|
10 месяцев назад |
 RedwindA
|
71b3c90bc9
解锁deepseek补全倍率；允许deepseek渠道获取模型
|
10 месяцев назад |
|
dd
|
40a6d957b5
Merge branch 'QuantumNous:main' into main
|
10 месяцев назад |
 CaIon
|
552d795742
Merge branch 'alpha'
|
10 месяцев назад |
|
creamlike1024
|
5cae6be108
feat: 支持 gemini-embedding-001
|
10 месяцев назад |
|
DD
|
71d41d6eaa
Merge branch 'main' of github.com:danding5/new-api
|
11 месяцев назад |
|
CaIon
|
1a8d781721
Revert "feat: gemini-2.5-flash-image-preview 文本和图片输出计费"
|
11 месяцев назад |
|
DD
|
68d30225e5
merge
|
11 месяцев назад |
|
DD
|
2fb5fc231d
Merge branches 'main' and 'main' of github.com:danding5/new-api
|
11 месяцев назад |
|
DD
|
cfbc2df3f8
add submodel.ai
|
11 месяцев назад |
|
creamlike1024
|
ff4b5b3fd2
feat: improve ratio update
|
11 месяцев назад |
|
creamlike1024
|
2875dbba10
feat: 图像倍率，音频倍率和音频补全倍率配置
|
11 месяцев назад |
|
creamlike1024
|
a45513a7a6
feat: gemini-2.5-flash-image-preview 文本和图片输出计费
|
11 месяцев назад |
|
CaIon
|
a102bed25a
fix(model_ratio): update return value logic for gemini-2.5-flash-lite
|
11 месяцев назад |
|
CaIon
|
79c7d8f477
fix: improve model ratio handling for reserved models in getHardcodedCompletionModelRatio
|
11 месяцев назад |
|
CaIon
|
7e513ad06d
fix: update model ratio handling for GPT versions
|
11 месяцев назад |
 wzxjohn
|
28dd5f5f0c
feat(ratio): add ratio for OpenAI models
|
1 год назад |
|
CaIon
|
97ea8b6560
refactor: Introduce pre-consume quota and unify relay handlers
|
1 год назад |
|
CaIon
|
c833e07ee3
feat: add support for gpt-5 models and adjust temperature settings
|
1 год назад |
 Calcium-Ion
|
a5c2539c38
Merge pull request #1525 from HynoR/chore/gpt5
|
1 год назад |
 HynoR
|
660b129b75
feat: sync gpt-5 model ratio and support new reasoning effort
|
1 год назад |
|
RedwindA
|
87cfcf1190
feat: add default model ratio for gemini-2.5-flash-lite-preview-thinking model
|
1 год назад |
|
RedwindA
|
2ef6e340a8
feat: update FormatMatchingModelName to handle gemini-2.5-flash-lite model prefix
|
1 год назад |
