| .. |
|
ai360
|
28885feea2
fix: 360智能接口地址更新
|
1 ano atrás |
|
ali
|
344a799fcf
feat: add wan2.5-i2i-preview support
|
3 meses atrás |
|
aws
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
2 meses atrás |
|
baidu
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
2 meses atrás |
|
baidu_v2
|
a6a20a2069
Merge pull request #2296 from seefs001/fix/adapter-missing
|
3 meses atrás |
|
claude
|
3652dfdbd5
fix: check claudeResponse delta StopReason nil point
|
2 meses atrás |
|
cloudflare
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
cohere
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
coze
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
2 meses atrás |
|
deepseek
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
dify
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
gemini
|
da24a165d0
fix(gemini): handle minimal reasoning effort budget
|
2 meses atrás |
|
jimeng
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
jina
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
lingyiwanwu
|
ea0c99ac1b
Update Perplexity and 01 models
|
1 ano atrás |
|
minimax
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
mistral
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
mokaai
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
moonshot
|
451c594e34
Merge pull request #2334 from seefs001/feature/glm-coding
|
3 meses atrás |
|
ollama
|
25af6e6f77
fix: handle JSON parsing for thinking content in ollama stream and chat handlers
|
4 meses atrás |
|
openai
|
dbaba87c39
为Moonshot添加缓存tokens读取逻辑
|
2 meses atrás |
|
openrouter
|
6e6a96d19f
feat: enhance OpenRouter enterprise support with new settings and response handling
|
5 meses atrás |
|
palm
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
perplexity
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
replicate
|
d0c45a01fa
feat: replicate channel flux model
|
4 meses atrás |
|
siliconflow
|
c4ca9d7c3b
refactor(relay): enhance error logging and improve multipart form handling in audio requests #2127
|
4 meses atrás |
|
submodel
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
task
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
2 meses atrás |
|
tencent
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
vertex
|
28f7a4feef
fix: 在Vertex Adapter过滤content[].part[].functionResponse.id
|
2 meses atrás |
|
volcengine
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
xai
|
f5b409d74f
feat: refactor token estimation logic
|
3 meses atrás |
|
xinference
|
0689670698
🔧 fix(xinference): update Document type to 'any' for flexibility
|
8 meses atrás |
|
xunfei
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
zhipu
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
5 meses atrás |
|
zhipu_4v
|
21fca238bf
refactor(error): replace dto.OpenAIError with types.OpenAIError for consistency
|
2 meses atrás |
|
adapter.go
|
5889571108
fix: Use channel proxy settings for task query scenarios
|
3 meses atrás |
|
api_request.go
|
d4a2c2ab54
Revert "Gemini Image系列支持图像编辑"
|
3 meses atrás |
Calcium-Ion
654bb10b45
Merge pull request #2460 from seefs001/feature/gemini-flash-minial