| .. |
|
ai360
|
192fc094fc
fix: 360智能接口地址更新
|
1 ano atrás |
|
ali
|
010638a884
feat: add wan2.5-i2i-preview support
|
8 meses atrás |
|
aws
|
c2ed76ddfd
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
7 meses atrás |
|
baidu
|
c2ed76ddfd
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
7 meses atrás |
|
baidu_v2
|
d98e7b3dbf
Merge pull request #2296 from seefs001/fix/adapter-missing
|
8 meses atrás |
|
claude
|
a655801017
feat: add claude-haiku-4-5-20251001 model support
|
8 meses atrás |
|
cloudflare
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
cohere
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
coze
|
c2ed76ddfd
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
7 meses atrás |
|
deepseek
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
dify
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
gemini
|
39df47486c
fix(gemini): handle minimal reasoning effort budget
|
7 meses atrás |
|
jimeng
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
jina
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
lingyiwanwu
|
3f6aeaa0e3
Update Perplexity and 01 models
|
2 anos atrás |
|
minimax
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
mistral
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
mokaai
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
moonshot
|
0ba6004ffc
Merge pull request #2334 from seefs001/feature/glm-coding
|
8 meses atrás |
|
ollama
|
e4a2904c56
fix: handle JSON parsing for thinking content in ollama stream and chat handlers
|
9 meses atrás |
|
openai
|
3822f4577c
fix(audio): correct TotalTokens calculation for accurate usage reporting
|
7 meses atrás |
|
openrouter
|
6682842cbb
feat: enhance OpenRouter enterprise support with new settings and response handling
|
10 meses atrás |
|
palm
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
perplexity
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
replicate
|
af671d34c3
feat: replicate channel flux model
|
9 meses atrás |
|
siliconflow
|
5d12755798
refactor(relay): enhance error logging and improve multipart form handling in audio requests #2127
|
9 meses atrás |
|
submodel
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
task
|
c2ed76ddfd
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
7 meses atrás |
|
tencent
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
vertex
|
06c23ea562
fix(adaptor): fix reasoning suffix not processing in vertex adapter
|
8 meses atrás |
|
volcengine
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
xai
|
1fededceb3
feat: refactor token estimation logic
|
8 meses atrás |
|
xinference
|
038202b1f6
🔧 fix(xinference): update Document type to 'any' for flexibility
|
1 ano atrás |
|
xunfei
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
zhipu
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
10 meses atrás |
|
zhipu_4v
|
a1299114a6
refactor(error): replace dto.OpenAIError with types.OpenAIError for consistency
|
7 meses atrás |
|
adapter.go
|
920e005048
fix: Use channel proxy settings for task query scenarios
|
8 meses atrás |
|
api_request.go
|
b827d1f778
Revert "Gemini Image系列支持图像编辑"
|
8 meses atrás |
Seefs
39df47486c
fix(gemini): handle minimal reasoning effort budget