| .. |
|
ai360
|
192fc094fc
fix: 360智能接口地址更新
|
hai 1 ano |
|
ali
|
7efb1922fe
Merge pull request #3526 from feitianbubu/pr/e560265b6e57aa7b95bc98cb53397ef0a3082d9d
|
hai 2 meses |
|
aws
|
ad326beb10
Merge pull request #3066 from seefs001/fix/aws-header-override
|
hai 3 meses |
|
baidu
|
5238f279db
feat: record stream interruption reasons via StreamStatus
|
hai 2 meses |
|
baidu_v2
|
d98e7b3dbf
Merge pull request #2296 from seefs001/fix/adapter-missing
|
hai 6 meses |
|
claude
|
82c2008d2c
fix: emit claude message_delta for usage-only final stream chunk
|
hai 2 meses |
|
cloudflare
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
codex
|
7e68e1b36a
chore: update model lists for frequently used channels
|
hai 3 meses |
|
cohere
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
coze
|
fb76abb329
fix: update OpenAI request fields to use json.RawMessage for dynamic data handling
|
hai 3 meses |
|
deepseek
|
a972722367
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
|
hai 4 meses |
|
dify
|
5238f279db
feat: record stream interruption reasons via StreamStatus
|
hai 2 meses |
|
gemini
|
79527c0ab1
feat: add HEIC/HEIF image format support
|
hai 2 meses |
|
jimeng
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hai 8 meses |
|
jina
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hai 8 meses |
|
lingyiwanwu
|
3f6aeaa0e3
Update Perplexity and 01 models
|
%!s(int64=2) %!d(string=hai) anos |
|
minimax
|
7e68e1b36a
chore: update model lists for frequently used channels
|
hai 3 meses |
|
mistral
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
mokaai
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hai 8 meses |
|
moonshot
|
7e68e1b36a
chore: update model lists for frequently used channels
|
hai 3 meses |
|
ollama
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
openai
|
5238f279db
feat: record stream interruption reasons via StreamStatus
|
hai 2 meses |
|
openrouter
|
a4629f2630
feats: repair the thinking of claude to openrouter convert
|
hai 3 meses |
|
palm
|
1fededceb3
feat: refactor token estimation logic
|
hai 6 meses |
|
perplexity
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
replicate
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
siliconflow
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
submodel
|
5010f2d004
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hai 8 meses |
|
task
|
8fc0eb78e2
feat(billing): enhance task billing process with video input detection and updated pricing logic
|
hai 2 meses |
|
tencent
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
vertex
|
ad326beb10
Merge pull request #3066 from seefs001/fix/aws-header-override
|
hai 3 meses |
|
volcengine
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
xai
|
d22f889e5d
fix(xAI): set MaxTokens to nil when MaxCompletionTokens is 0 for grok-3-mini model
|
hai 2 meses |
|
xinference
|
038202b1f6
🔧 fix(xinference): update Document type to 'any' for flexibility
|
hai 11 meses |
|
xunfei
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
zhipu
|
2cf3c1836c
fix: preserve explicit zero values in native relay requests
|
hai 3 meses |
|
zhipu_4v
|
7e68e1b36a
chore: update model lists for frequently used channels
|
hai 3 meses |
|
adapter.go
|
8374a83084
feat(task): add adaptor billing interface and async settlement framework
|
hai 3 meses |
|
api_request.go
|
42500b3317
fix: fetch model add header passthrough rule key check
|
hai 3 meses |
|
api_request_test.go
|
a955d4102d
refactor(override): simplify header overrides to a lowercase single map
|
hai 3 meses |
CaIon
8fc0eb78e2
feat(billing): enhance task billing process with video input detection and updated pricing logic