feat: 算力配置全面审计 — 6 家供应商 + Token/Coding Plan 对齐官方文档 (#20)

Providers:
- moonshot: 移除到期模型 kimi-k2/k2-thinking,修正 k2.6 maxOutputTokens 32768、k2.5 contextWindow 262144
- tencent: 修正 hunyuan-t1-latest 上下文/输出/价格,新增 hunyuan-t1-vision/turbos-vision
- volcengine: doubao-seed-2.0-lite/mini 新增 audio_understanding/video_understanding
- internal-testing: services 扩展为全部 18 种类型,新增 mediaBaseUrl

Coding Plans:
- dashscope-token-plan: baseUrl 修正为 coding.dashscope.aliyuncs.com,移除非 Coding Plan 模型,新增 kimi-k2.5/qwen3.5-plus/qwen3-coder-plus/glm-4.7
- minimax-coding: 修正 usageTracking 端点,services 扩展为 7 种含媒体类型
- moonshot-coding: maxOutputTokens 修正为 32768
- zhipu-coding: 新增 glm-5.1/glm-5-turbo/glm-4.5-air,修正 glm-5 contextWindow 200000
- volcengine-coding: 新增 glm-5.1/kimi-k2.6/minimax-m2.7
- tencent-token: 新增腾讯云 Token Plan(10 个模型)

presetDataVersion: 45 → 46
This commit is contained in:
2026-05-10 00:58:56 +08:00
committed by GitHub
parent 82ad03d9eb
commit 00e148af8e
12 changed files with 553 additions and 156 deletions

View File

@@ -68,7 +68,7 @@
"serviceType": [
"chat"
],
"description": "火山引擎豆包 Seed 2.0 均衡模型256K上下文适合通用生产任务",
"description": "火山引擎豆包 Seed 2.0 全模态均衡模型256K上下文支持视频/图像/音频/文本统一理解",
"contextWindow": 256000,
"maxOutputTokens": 32000,
"capabilities": [
@@ -78,7 +78,9 @@
"multilingual",
"long_context",
"tool_use",
"vision"
"vision",
"audio_understanding",
"video_understanding"
],
"inputPrice": 0.6,
"outputPrice": 3.6,
@@ -110,7 +112,7 @@
"serviceType": [
"chat"
],
"description": "火山引擎豆包 Seed 2.0 轻量模型256K上下文适合低延迟高并发场景",
"description": "火山引擎豆包 Seed 2.0 全模态轻量模型256K上下文低延迟高并发,支持全模态理解",
"contextWindow": 256000,
"maxOutputTokens": 32000,
"capabilities": [
@@ -121,6 +123,8 @@
"long_context",
"tool_use",
"vision",
"audio_understanding",
"video_understanding",
"fast"
],
"inputPrice": 0.2,