| .. |
|
ai360
|
28885feea2
fix: 360智能接口地址更新
|
hace 1 año |
|
ali
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
aws
|
c9f5de7048
feat: support adaptive thinking
|
hace 2 meses |
|
baidu
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
hace 3 meses |
|
baidu_v2
|
a6a20a2069
Merge pull request #2296 from seefs001/fix/adapter-missing
|
hace 4 meses |
|
claude
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
cloudflare
|
f5b409d74f
feat: refactor token estimation logic
|
hace 4 meses |
|
codex
|
742f4ad1e4
Merge pull request #2883 from seefs001/fix/claude-relay-info-input-token
|
hace 1 mes |
|
cohere
|
f5b409d74f
feat: refactor token estimation logic
|
hace 4 meses |
|
coze
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
hace 3 meses |
|
deepseek
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
dify
|
f5b409d74f
feat: refactor token estimation logic
|
hace 4 meses |
|
gemini
|
ecebd619a4
fix: charge local input tokens when Gemini returns empty response
|
hace 2 meses |
|
jimeng
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
jina
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
lingyiwanwu
|
ea0c99ac1b
Update Perplexity and 01 models
|
hace 1 año |
|
minimax
|
c975b4cfa8
fix(minimax): 添加 MiniMax-M2 系列模型到 ModelList
|
hace 2 meses |
|
mistral
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
mokaai
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
moonshot
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
ollama
|
9ef7740fe7
feat(file): unify file handling with a new FileSource abstraction for URL and base64 data
|
hace 2 meses |
|
openai
|
b580b8bd1d
fix: add paragraph breaks between reasoning summary chunks in chat2responses stream
|
hace 1 mes |
|
openrouter
|
6e6a96d19f
feat: enhance OpenRouter enterprise support with new settings and response handling
|
hace 6 meses |
|
palm
|
f5b409d74f
feat: refactor token estimation logic
|
hace 4 meses |
|
perplexity
|
b6dc75cb86
feat: /v1/responses perplexity
|
hace 2 meses |
|
replicate
|
d0c45a01fa
feat: replicate channel flux model
|
hace 5 meses |
|
siliconflow
|
c4ca9d7c3b
refactor(relay): enhance error logging and improve multipart form handling in audio requests #2127
|
hace 5 meses |
|
submodel
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
task
|
df465ca8fd
feat: doubao add first and last image to video
|
hace 2 meses |
|
tencent
|
f5b409d74f
feat: refactor token estimation logic
|
hace 4 meses |
|
vertex
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
volcengine
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
xai
|
f5b409d74f
feat: refactor token estimation logic
|
hace 4 meses |
|
xinference
|
0689670698
🔧 fix(xinference): update Document type to 'any' for flexibility
|
hace 9 meses |
|
xunfei
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
zhipu
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hace 5 meses |
|
zhipu_4v
|
a0bb78edd0
fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑
|
hace 1 mes |
|
adapter.go
|
5889571108
fix: Use channel proxy settings for task query scenarios
|
hace 3 meses |
|
api_request.go
|
b55e42eda7
feat(api): add 'cookie' to passthroughSkipHeaderNamesLower
|
hace 2 meses |
Calcium-Ion
742f4ad1e4
Merge pull request #2883 from seefs001/fix/claude-relay-info-input-token