huangzhenpc/new-api-hunter
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,465 Commits 1 Branch 0 Tags
c41ca95a43679ec7853e43556b8283a15676602b
Commit Graph

72 Commits

Author SHA1 Message Date
huangzhenpc
c41ca95a43 fix: 管理员自定义价格的任务模型自动按次计费，不再乘 OtherRatios 
当管理员为任务模型（如 sora_video2）设置了固定价格时，
之前会错误地将价格乘以 seconds/size 等 OtherRatios，
导致设置 $2/次 实际收费 $8（$2 × 4秒）。

新增 IsTaskPerCallBilling() 判断逻辑：
- 模型在 TASK_PRICE_PATCH 环境变量中 → 按次（兼容旧逻辑）
- 模型有管理员配置的价格且不在默认价格表中 → 自动按次
默认价格表中的模型（如 sora-2: $0.3）仍按原逻辑乘 OtherRatios。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-24 17:01:12 +08:00
CaIon
deff59a5be fix: increase StreamScannerMaxBufferMB limit and add handling for gpt-5.4-nano prefix 2026-03-22 13:55:10 +08:00
CaIon
c0a0285f74 fix: update language settings and improve model pricing editor for better clarity and functionality 2026-03-06 21:36:51 +08:00
CaIon
5372d9ba55 fix: add support for gpt-5.4 model in model_ratio.go 2026-03-06 11:43:05 +08:00
CaIon
32d9ae1f83 feat(gemini): implement video generation configuration and billing estimation 
- Added Gemini video generation configuration structures and payloads.
- Introduced functions for parsing and resolving video duration and resolution from metadata.
- Enhanced the Vertex adaptor to support Gemini video generation requests and billing estimation based on duration and resolution.
- Updated model pricing settings for new Gemini video models.
 2026-02-28 17:37:08 +08:00
RedwindA
b2898b392a fix: adjust default Gemini cache ratios 2026-02-20 12:28:30 +08:00
CaIon
aed8c07cd7 refactor(ratio): replace maps with RWMap for improved concurrency handling 2026-02-08 00:48:21 +08:00
Seefs
8ef6089bf7 feat: make 5m cache-creation ratio configurable 2026-02-06 19:46:59 +08:00
Papersnake
e194b747c3 feat: support adaptive thinking 2026-02-06 11:01:23 +08:00
Papersnake
7ca072b1b0 feat: add claude-opus-4-6 2026-02-06 09:12:45 +08:00
CaIon
330e1e6395 remove: drop support for claude-2 and claude-1 series models 
- Remove claude-instant-1.2, claude-2, claude-2.0, claude-2.1 from model lists
- Remove /v1/complete endpoint support (legacy completion API)
- Remove RequestModeCompletion and related code paths
- Simplify handler functions by removing requestMode parameter
- Update all channel adaptors that referenced claude handlers
 2026-02-05 17:20:46 +08:00
RedwindA
3985d10ae1 feat(gemini): support cached token billing 2026-02-01 22:50:47 +08:00
Seefs
4f6d92ce7b fix: /v1/responses/compact default billing 2026-01-28 14:22:34 +08:00
Seefs
cf114ca7d6 feat: openai response /v1/response/compact (#2644) 
* feat: openai response /v1/response/compact

* feat: /v1/response/compact bill

* feat: /v1/response/compact

* feat: /v1/responses/compact -> codex channel

* feat: /v1/responses/compact -> codex channel

* feat: /v1/responses/compact -> codex channel

* feat: codex channel default models

* feat: compact model price

* feat: /v1/responses/comapct test
 2026-01-26 20:20:16 +08:00
CaIon
87a75b0565 feat(ratio): add functions to check for audio ratios and clean up unused code 2025-12-31 21:29:10 +08:00
CaIon
7bbb7f8114 feat(model): add audio ratios for new TTS models and adjust default values 2025-12-31 21:22:33 +08:00
Seefs
0edef97413 fix: revert model ratio 2025-12-25 15:37:54 +08:00
CaIon
06d1bd404b feat(model_ratio): add default ratios for gpt-4o-mini-tts 2025-12-13 19:14:27 +08:00
CaIon
be2a863b9b feat(audio): enhance audio request handling with token type detection and streaming support 2025-12-13 17:24:23 +08:00
FlowerRealm
a655801017 feat: add claude-haiku-4-5-20251001 model support 
- Add model to Claude ModelList
- Add model ratio (0.5, $1/1M input tokens)
- Add completion ratio support (5x, $5/1M output tokens)
- Add cache read ratio (0.1, $0.10/1M tokens)
- Add cache write ratio (1.25, $1.25/1M tokens)

Model specs:
- Context window: 200K tokens
- Max output: 64K tokens
- Release date: October 1, 2025
 2025-12-05 18:54:20 +08:00
Seefs
607f7305b7 feat: gemini 3 thinking level gemini-3-pro-preview-high 2025-12-01 16:40:46 +08:00
Papersnake
766b6bc795 feat: add claude-opus-4-5-20251101 2025-11-25 10:53:01 +08:00
Papersnake
113ca72ae9 feat: add claude-opus-4-5-20251101 ratio 2025-11-25 10:49:34 +08:00
CaIon
c8bbf7bed8 feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels 2025-11-21 18:17:01 +08:00
Xyfacai
a4bfec164e fix: 未设置价格模型不会被拉取，除非设置自用模式 2025-11-13 18:44:18 +08:00
Sh1n3zZ
af671d34c3 feat: replicate channel flux model 2025-11-08 01:24:45 +08:00
CaIon
6aec088693 feat: add special user usable group setting 2025-10-28 23:25:43 +08:00
Seefs
5010f2d004 format: package name -> github.com/QuantumNous/new-api (#2017) 2025-10-11 15:30:09 +08:00
Xyfacai
09495c8ef6 feat: sora 增加参数校验与计费 2025-10-10 23:56:36 +08:00
creamlike1024
eeef719f3a feat: 支持 gemini-robotics-er-1.5-preview 2025-10-01 17:33:54 +08:00
Seefs
740c46102b Merge pull request #1924 from prnake/claude-4-5 
feat: support claude-sonnet-4-5-20250929
 2025-09-30 09:26:34 +08:00
papersnake
112ab0b17c feat: support claude-sonnet-4-5-20250929 2025-09-30 09:14:12 +08:00
dd
f9399e279c Merge branch 'QuantumNous:main' into main 2025-09-29 19:15:43 +08:00
RedwindA
71b3c90bc9 解锁deepseek补全倍率；允许deepseek渠道获取模型 2025-09-29 18:32:44 +08:00
dd
40a6d957b5 Merge branch 'QuantumNous:main' into main 2025-09-29 14:13:50 +08:00
CaIon
552d795742 Merge branch 'alpha' 2025-09-19 14:20:15 +08:00
creamlike1024
5cae6be108 feat: 支持 gemini-embedding-001 2025-09-19 00:24:01 +08:00
DD
71d41d6eaa Merge branch 'main' of github.com:danding5/new-api 
# Conflicts:
#	relay/relay_adaptor.go
 2025-09-15 14:31:06 +08:00
creamlike1024
d21886b9fb Merge branch 'alpha' into imageratio-and-audioratio-edit 2025-09-15 14:12:24 +08:00
CaIon
1a8d781721 Revert "feat: gemini-2.5-flash-image-preview 文本和图片输出计费" 
This reverts commit a45513a7a6.
 2025-09-13 12:53:28 +08:00
DD
68d30225e5 merge 2025-09-10 19:11:58 +08:00
DD
2fb5fc231d Merge branches 'main' and 'main' of github.com:danding5/new-api 
# Conflicts:
#	common/api_type.go
#	constant/api_type.go
#	constant/channel.go
#	relay/relay_adaptor.go
#	web/src/constants/channel.constants.js
 2025-09-10 18:33:42 +08:00
DD
cfbc2df3f8 add submodel.ai 2025-09-08 16:21:21 +08:00
Seefs
80cfa0d0df Merge pull request #1677 from QuantumNous/gemini-2.5-flash-image-preview-billing 
feat: gemini-2.5-flash-image-preview 文本和图片输出计费
 2025-09-07 14:15:24 +08:00
t0ng7u
ed71c9fcf3 🎨 style(go): format entire codebase 
- Apply canonical Go formatting to all .go files
- No functional changes; whitespace/import/struct layout only
- Improves consistency, reduces diff noise, and aligns with standard tooling
 2025-08-31 13:08:34 +08:00
creamlike1024
ff4b5b3fd2 feat: improve ratio update 2025-08-30 23:53:46 +08:00
creamlike1024
2875dbba10 feat: 图像倍率，音频倍率和音频补全倍率配置 2025-08-30 23:28:09 +08:00
creamlike1024
a45513a7a6 feat: gemini-2.5-flash-image-preview 文本和图片输出计费 2025-08-27 21:30:52 +08:00
CaIon
a102bed25a fix(model_ratio): update return value logic for gemini-2.5-flash-lite 2025-08-26 23:01:00 +08:00
CaIon
79c7d8f477 fix: improve model ratio handling for reserved models in getHardcodedCompletionModelRatio 2025-08-25 11:59:55 +08:00