| .. |
|
ai360
|
28885feea2
fix: 360智能接口地址更新
|
vor 1 Jahr |
|
ali
|
2c29993cfc
feat: /v1/responses qwen3 max
|
vor 3 Monaten |
|
aws
|
5f37a1e97c
fix: fix the proxyURL is empty, not using the default HTTP client configuration && the AWS calling side did not apply the relay timeout.
|
vor 4 Monaten |
|
baidu
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
vor 4 Monaten |
|
baidu_v2
|
a6a20a2069
Merge pull request #2296 from seefs001/fix/adapter-missing
|
vor 5 Monaten |
|
claude
|
760fbeb6e6
Merge pull request #2811 from seefs001/fix/openrouter-claude-cache-usage
|
vor 3 Monaten |
|
cloudflare
|
f5b409d74f
feat: refactor token estimation logic
|
vor 5 Monaten |
|
codex
|
cc1da72d10
feat: openai response /v1/response/compact (#2644)
|
vor 3 Monaten |
|
cohere
|
f5b409d74f
feat: refactor token estimation logic
|
vor 5 Monaten |
|
coze
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
vor 4 Monaten |
|
deepseek
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
dify
|
f5b409d74f
feat: refactor token estimation logic
|
vor 5 Monaten |
|
gemini
|
5d6044f479
merge github
|
vor 3 Monaten |
|
jimeng
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
jina
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
lingyiwanwu
|
ea0c99ac1b
Update Perplexity and 01 models
|
vor 1 Jahr |
|
minimax
|
c975b4cfa8
fix(minimax): 添加 MiniMax-M2 系列模型到 ModelList
|
vor 3 Monaten |
|
mistral
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
mokaai
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
moonshot
|
451c594e34
Merge pull request #2334 from seefs001/feature/glm-coding
|
vor 5 Monaten |
|
ollama
|
725d61c5d3
feat: ionet integrate (#2105)
|
vor 4 Monaten |
|
openai
|
cc1da72d10
feat: openai response /v1/response/compact (#2644)
|
vor 3 Monaten |
|
openrouter
|
6e6a96d19f
feat: enhance OpenRouter enterprise support with new settings and response handling
|
vor 7 Monaten |
|
palm
|
f5b409d74f
feat: refactor token estimation logic
|
vor 5 Monaten |
|
perplexity
|
b6dc75cb86
feat: /v1/responses perplexity
|
vor 3 Monaten |
|
replicate
|
d0c45a01fa
feat: replicate channel flux model
|
vor 6 Monaten |
|
siliconflow
|
c4ca9d7c3b
refactor(relay): enhance error logging and improve multipart form handling in audio requests #2127
|
vor 6 Monaten |
|
submodel
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
task
|
df465ca8fd
feat: doubao add first and last image to video
|
vor 3 Monaten |
|
tencent
|
f5b409d74f
feat: refactor token estimation logic
|
vor 5 Monaten |
|
vertex
|
cbebd15692
fix: vertex maas api addr (#2810)
|
vor 3 Monaten |
|
volcengine
|
67ba913b44
feat: add support for Doubao /v1/responses (#2567)
|
vor 4 Monaten |
|
xai
|
f5b409d74f
feat: refactor token estimation logic
|
vor 5 Monaten |
|
xinference
|
0689670698
🔧 fix(xinference): update Document type to 'any' for flexibility
|
vor 10 Monaten |
|
xunfei
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
zhipu
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
vor 6 Monaten |
|
zhipu_4v
|
21fca238bf
refactor(error): replace dto.OpenAIError with types.OpenAIError for consistency
|
vor 4 Monaten |
|
adapter.go
|
5889571108
fix: Use channel proxy settings for task query scenarios
|
vor 4 Monaten |
|
api_request.go
|
0d5ae12ebc
fix: make channel Host override take effect
|
vor 3 Monaten |
supeng
5d6044f479
merge github