Files
config-center/compute/model-specs/_index.json
Yige 73b278df51 fix(compute): GLM-5.3 系列在 anthropic 协议按官网用 output_config.effort 控制思考强度 (#120)
智谱官网(国内 coding-plan/latest-model、国际 devpack/latest-model)写明 /api/anthropic
以 thinking.type 与 output_config.effort 控制思考强度,thinking.type=enabled 一律按默认 max
处理,budget_tokens 不是控制项。两个 anthropic-messages 接入面的 GLM-5.3 系列此前只有按
OpenAI 协议文档写的 low/high/max 矩阵,客户端按 budget 形态发送:low/high 在上游都成了 max,
max(也是默认档)在客户端本机被拒绝;经 new-api 的 OpenAI 类渠道转换时 low 变成
reasoning_effort=medium,被智谱标准 API 拒绝。

- zhipu、zhipu-coding 接入面的 GLM-5.3 / 5.3-Flash / 5.3-FlashX 声明 adaptiveThinking
- GLM-5.3 系列规格加 anthropic-messages 协议 profile(V1 副本为 spec.extra.adaptiveThinking),
  覆盖经 ModelSpec 补全的云端条目
- 来源记录补国际 Coding Plan 页;按量 API Key 与 FlashX 按同一端点推定,未列入已核字段
- presetDataVersion 130
2026-10-05 09:17:43 -07:00

64 lines
1.9 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"description": "模型规格库加载顺序索引,以及智能路由三档的同域定义。模型级路由策略仅写入各 ModelSpec 的 routing 字段,不另建 smart-routing 目录。 数据批次 130:GLM-5.3 系列在 anthropic-messages 协议上按智谱官网以 thinking.type 与 output_config.effort 控制思考强度(protocolProfiles 声明 adaptive 形态),路由策略不变;此前批次 129 按官网补对话规格的 tool_use 标签,批次 126 为官方字段复核与临时、历史规格边界。 精确身份治理:隔离Nano/实时/固定变体,identity-only不继承family参数;发布批次由manifest统一标记。",
"order": [
"anthropic",
"openai",
"google",
"deepseek",
"qwen",
"wan",
"moonshot",
"zhipu",
"minimax",
"xai",
"mistral",
"xiaomi",
"baichuan",
"baidu",
"cohere",
"kling",
"perplexity",
"stability",
"tencent",
"volcengine",
"xunfei",
"stealth",
"happyhorse"
],
"routingTiers": [
{
"id": "flagship",
"label": "旗舰",
"labelEn": "Flagship",
"description": "最高能力,适合复杂推理、关键交付和长程智能体任务。",
"fallbackOrder": [
"flagship",
"balanced",
"lightweight"
]
},
{
"id": "balanced",
"label": "均衡",
"labelEn": "Balanced",
"description": "质量、速度与成本平衡,适合大多数日常任务。",
"fallbackOrder": [
"balanced",
"flagship",
"lightweight"
]
},
{
"id": "lightweight",
"label": "轻量",
"labelEn": "Lightweight",
"description": "优先低延迟与低成本,适合明确、短链路和批量任务。",
"fallbackOrder": [
"lightweight",
"balanced",
"flagship"
]
}
]
}