Calcium-Ion 47cdac3e64 Merge pull request #2883 from seefs001/fix/claude-relay-info-input-token ...

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

2026-02-08 00:17:50 +08:00

..

ai360

fix: 360智能接口地址更新

2024-12-02 15:59:08 +00:00

ali

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

2026-02-07 14:21:19 +08:00

aws

feat: support adaptive thinking

2026-02-06 11:01:23 +08:00

baidu

🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled

2025-12-16 17:00:19 +08:00

baidu_v2

Merge pull request #2296 from seefs001/fix/adapter-missing

2025-11-25 16:45:14 +08:00

claude

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

2026-02-07 14:21:19 +08:00

cloudflare

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

codex

Merge pull request #2883 from seefs001/fix/claude-relay-info-input-token

2026-02-08 00:17:50 +08:00

cohere

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

coze

🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled

2025-12-16 17:00:19 +08:00

deepseek

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

2026-02-07 14:21:19 +08:00

dify

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

gemini

fix: charge local input tokens when Gemini returns empty response

2026-02-05 15:57:17 +08:00

jimeng

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

jina

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

lingyiwanwu

Update Perplexity and 01 models

2024-05-17 19:37:18 +08:00

minimax

fix(minimax): 添加 MiniMax-M2 系列模型到 ModelList

2026-01-09 20:46:47 +08:00

mistral

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

mokaai

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

moonshot

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

2026-02-07 14:21:19 +08:00

ollama

feat(file): unify file handling with a new FileSource abstraction for URL and base64 data

2026-02-04 18:23:17 +08:00

openai

fix: add paragraph breaks between reasoning summary chunks in chat2responses stream

2026-02-06 14:46:29 +08:00

openrouter

feat: enhance OpenRouter enterprise support with new settings and response handling

2025-09-28 15:23:27 +08:00

palm

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

perplexity

feat: /v1/responses perplexity

2026-02-02 14:48:45 +08:00

replicate

feat: replicate channel flux model

2025-11-08 01:24:45 +08:00

siliconflow

refactor(relay): enhance error logging and improve multipart form handling in audio requests #2127

2025-10-29 23:33:55 +08:00

submodel

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

task

feat: doubao add first and last image to video

2026-01-27 17:33:00 +08:00

tencent

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

vertex

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

2026-02-07 14:21:19 +08:00

volcengine

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

2026-02-07 14:21:19 +08:00

xai

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

xinference

🔧 fix(xinference): update Document type to 'any' for flexibility

2025-06-25 18:04:34 +08:00

xunfei

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

zhipu

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00

zhipu_4v

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

2026-02-07 14:21:19 +08:00

adapter.go

fix: Use channel proxy settings for task query scenarios

2025-12-09 11:15:27 +08:00

api_request.go

feat(api): add 'cookie' to passthroughSkipHeaderNamesLower

2026-02-05 22:16:35 +08:00