Skip to content

Commit 511b14a

Browse files
gujieyegujieye
committed
chore: update bailian-docs-llm-wiki (2026-09-22)
1 parent 973f2e9 commit 511b14a

559 files changed

Lines changed: 17663 additions & 14244 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎skills/bailian-docs-llm-wiki/llms.txt‎

Lines changed: 768 additions & 745 deletions
Large diffs are not rendered by default.

‎skills/bailian-docs-llm-wiki/models/families.jsonl‎

Lines changed: 12 additions & 9 deletions
Large diffs are not rendered by default.

‎skills/bailian-docs-llm-wiki/models/groups/deepseek.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -167,6 +167,7 @@
167167
"maxInputTokens": 1000000,
168168
"inferenceProvider": "aliyun-bailian",
169169
"name": "DeepSeek-V4.1-Flash",
170+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/deepseek-api",
170171
"category": "Third-party",
171172
"samples": {
172173
"openai": {

‎skills/bailian-docs-llm-wiki/models/groups/glm-4.5.json‎

Lines changed: 124 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1075,6 +1075,130 @@
10751075
}
10761076
}
10771077
}
1078+
},
1079+
{
1080+
"inferenceMetadata": {
1081+
"response_modality": [
1082+
"Text"
1083+
],
1084+
"request_modality": [
1085+
"Text"
1086+
]
1087+
},
1088+
"builtInToolMultiPrices": [
1089+
{
1090+
"supportedApi": "Responses API",
1091+
"name": "code_interpreter",
1092+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/qwen-code-interpreter",
1093+
"type": "code_interpreter",
1094+
"prices": [
1095+
{
1096+
"priceUnit": "",
1097+
"price": "0",
1098+
"currency": "CNY"
1099+
}
1100+
]
1101+
},
1102+
{
1103+
"supportedApi": "Responses API",
1104+
"name": "web_extractor",
1105+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/web-extractor",
1106+
"type": "web_extractor",
1107+
"prices": [
1108+
{
1109+
"priceUnit": "",
1110+
"price": "0",
1111+
"currency": "CNY"
1112+
}
1113+
]
1114+
}
1115+
],
1116+
"description": "GLM-5.3-Prime 是 GLM-5.3 的高速版本，编程与智能体能力全面进阶，达开源模型 SOTA 水平，内部编程基准较上代提升 50%，可端到端交付生产级成果。涌现网络安全能力，漏洞发现基准 CyberGym 创当前最佳。支持 1M 上下文、128K 输出与三档深度思考，胜任长程复杂任务。",
1117+
"features": [
1118+
"cache",
1119+
"function-calling",
1120+
"model-experience",
1121+
"structured-outputs"
1122+
],
1123+
"provider": "zhipu-ai",
1124+
"model": "glm-5.3-prime",
1125+
"prices": [
1126+
{
1127+
"priceUnit": "每百万tokens",
1128+
"price": "16",
1129+
"timeBand": "standard",
1130+
"ntmAmountType": "input_token",
1131+
"type": "input_token",
1132+
"priceName": "输入"
1133+
},
1134+
{
1135+
"priceUnit": "每百万tokens",
1136+
"price": "56",
1137+
"timeBand": "standard",
1138+
"ntmAmountType": "output_token",
1139+
"type": "output_token",
1140+
"priceName": "输出"
1141+
},
1142+
{
1143+
"priceUnit": "每百万tokens",
1144+
"price": "4",
1145+
"timeBand": "standard",
1146+
"ntmAmountType": "input_token_cache",
1147+
"type": "input_token_cache",
1148+
"priceName": "输入（缓存命中）"
1149+
}
1150+
],
1151+
"qpmInfo": {
1152+
"model-default-actual": {
1153+
"usage_limit": 200000,
1154+
"usage_limit_field": "total_tokens",
1155+
"usage_limit_period": 6,
1156+
"type": "model-default"
1157+
},
1158+
"model-default": {
1159+
"usage_limit": 200000,
1160+
"usage_limit_field": "total_tokens",
1161+
"usage_limit_period": 6,
1162+
"type": "model-default"
1163+
}
1164+
},
1165+
"priceTimeBands": [
1166+
"standard"
1167+
],
1168+
"capabilities": [
1169+
"TG",
1170+
"Reasoning"
1171+
],
1172+
"versionTag": "MAJOR",
1173+
"maxOutputTokens": 131072,
1174+
"latestOnlineAt": "2026-09-21T05:35:15.000+00:00",
1175+
"inferenceSpeeds": [
1176+
"prime"
1177+
],
1178+
"contextWindow": 1000000,
1179+
"maxInputTokens": 1048576,
1180+
"inferenceProvider": "aliyun-bailian",
1181+
"name": "GLM-5.3-Prime",
1182+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/glm",
1183+
"category": "Third-party",
1184+
"samples": {
1185+
"openai": {
1186+
"default": {
1187+
"curl": "curl -X POST https://[workspace-id].cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions \\\n-H \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n \"model\": \"glm-5.3-prime\",\n \"messages\": [\n {\n \"role\": \"user\", \n \"content\": \"你是谁\"\n }\n ],\n \"stream\": true,\n \"enable_thinking\": true\n}'",
1188+
"python": "from openai import OpenAI\nimport os\n\nclient = OpenAI(\n # 如果没有配置环境变量，请用阿里云百炼API Key替换：api_key=\"sk-xxx\"\n api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n base_url=\"https://[workspace-id].cn-beijing.maas.aliyuncs.com/compatible-mode/v1\",\n)\n\nmessages = [{\"role\": \"user\", \"content\": \"你是谁\"}]\ncompletion = client.chat.completions.create(\n model=\"glm-5.3-prime\", # 您可以按需更换为其它深度思考模型\n messages=messages,\n extra_body={\"enable_thinking\": True},\n stream=True\n)\nis_answering = False # 是否进入回复阶段\nprint(\"\\n\" + \"=\" * 20 + \"思考过程\" + \"=\" * 20)\nfor chunk in completion:\n delta = chunk.choices[0].delta\n if hasattr(delta, \"reasoning_content\") and delta.reasoning_content is not None:\n if not is_answering:\n print(delta.reasoning_content, end=\"\", flush=True)\n if hasattr(delta, \"content\") and delta.content:\n if not is_answering:\n print(\"\\n\" + \"=\" * 20 + \"完整回复\" + \"=\" * 20)\n is_answering = True\n print(delta.content, end=\"\", flush=True)",
1189+
"nodejs": "from openai import OpenAI\nimport os\n\nclient = OpenAI(\n # 如果没有配置环境变量，请用阿里云百炼API Key替换：api_key=\"sk-xxx\"\n api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n base_url=\"https://[workspace-id].cn-beijing.maas.aliyuncs.com/compatible-mode/v1\",\n)\n\nmessages = [{\"role\": \"user\", \"content\": \"你是谁\"}]\ncompletion = client.chat.completions.create(\n model=\"glm-5.3-prime\", # 您可以按需更换为其它深度思考模型\n messages=messages,\n extra_body={\"enable_thinking\": True},\n stream=True\n)\nis_answering = False # 是否进入回复阶段\nprint(\"\\n\" + \"=\" * 20 + \"思考过程\" + \"=\" * 20)\nfor chunk in completion:\n delta = chunk.choices[0].delta\n if hasattr(delta, \"reasoning_content\") and delta.reasoning_content is not None:\n if not is_answering:\n print(delta.reasoning_content, end=\"\", flush=True)\n if hasattr(delta, \"content\") and delta.content:\n if not is_answering:\n print(\"\\n\" + \"=\" * 20 + \"完整回复\" + \"=\" * 20)\n is_answering = True\n print(delta.content, end=\"\", flush=True)",
1190+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/glm"
1191+
}
1192+
},
1193+
"dashscope": {
1194+
"default": {
1195+
"curl": "curl -X POST \"https://[workspace-id].cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation\" \\\n-H \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n \"model\": \"glm-5.3-prime\",\n \"input\":{\n \"messages\":[\n {\n \"role\": \"user\",\n \"content\": \"你是谁？\"\n }\n ]\n },\n \"parameters\":{\n \"enable_thinking\": true,\n \"result_format\": \"message\"\n }\n}'",
1196+
"python": "import os\nfrom dashscope import Generation\nimport dashscope\ndashscope.base_http_api_url = 'https://[workspace-id].cn-beijing.maas.aliyuncs.com/api/v1'\n\nmessages = [\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"你是谁？\"},\n]\nresponse = Generation.call(\n # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = \"sk-xxx\",\n api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n model=\"glm-5.3-prime\",\n messages=messages,\n result_format=\"message\",\n # 开启深度思考\n enable_thinking=True,\n)\n\nif response.status_code == 200:\n # 打印思考过程\n print(\"=\" * 20 + \"思考过程\" + \"=\" * 20)\n print(response.output.choices[0].message.reasoning_content)\n \n # 打印回复\n print(\"=\" * 20 + \"完整回复\" + \"=\" * 20)\n print(response.output.choices[0].message.content)\nelse:\n print(f\"HTTP返回码：{response.status_code}\")\n print(f\"错误码：{response.code}\")\n print(f\"错误信息：{response.message}\")",
1197+
"java": "import java.util.Arrays;\nimport java.lang.System;\nimport com.alibaba.dashscope.aigc.generation.Generation;\nimport com.alibaba.dashscope.aigc.generation.GenerationParam;\nimport com.alibaba.dashscope.aigc.generation.GenerationResult;\nimport com.alibaba.dashscope.common.Message;\nimport com.alibaba.dashscope.common.Role;\nimport com.alibaba.dashscope.exception.ApiException;\nimport com.alibaba.dashscope.exception.InputRequiredException;\nimport com.alibaba.dashscope.exception.NoApiKeyException;\nimport com.alibaba.dashscope.utils.Constants;\n\npublic class Main {\n static {\n Constants.baseHttpApiUrl=\"https://[workspace-id].cn-beijing.maas.aliyuncs.com/api/v1\";\n }\n public static GenerationResult callWithMessage() throws ApiException, NoApiKeyException, InputRequiredException {\n Generation gen = new Generation();\n Message systemMsg = Message.builder()\n .role(Role.SYSTEM.getValue())\n .content(\"You are a helpful assistant.\")\n .build();\n Message userMsg = Message.builder()\n .role(Role.USER.getValue())\n .content(\"你是谁？\")\n .build();\n GenerationParam param = GenerationParam.builder()\n // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey(\"sk-xxx\")\n .apiKey(System.getenv(\"DASHSCOPE_API_KEY\"))\n .model(\"glm-5.3-prime\")\n .messages(Arrays.asList(systemMsg, userMsg))\n .resultFormat(GenerationParam.ResultFormat.MESSAGE)\n .enableThinking(true)\n .build();\n return gen.call(param);\n }\n public static void main(String[] args) {\n try {\n GenerationResult result = callWithMessage();\n System.out.println(\"====================思考过程====================\");\n System.out.println(result.getOutput().getChoices().get(0).getMessage().getReasoningContent());\n System.out.println(\"\\n====================完整回复====================\");\n System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent());\n } catch (ApiException | NoApiKeyException | InputRequiredException e) {\n System.err.println(\"错误信息：\"+e.getMessage());\n }\n }\n}",
1198+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/glm"
1199+
}
1200+
}
1201+
}
10781202
}
10791203
]
10801204
}

skills/bailian-docs-llm-wiki/models/groups/qwen-audio-asr-flash.json renamed to skills/bailian-docs-llm-wiki/models/groups/qwen-audio-3.0-asr.json

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
2-
"name": "Qwen-Audio-ASR-Flash",
3-
"description": "Qwen-Audio-ASR-Flash是一款支持短语音高效识别的大模型，面向高质量、多语种及文化内容转写场景。模型支持多语种与多地区中文方言识别，同时针对中文古诗词的韵律、节奏与文言表达进行优化。具备上下文增强、标点预测与文本规范化能力。",
2+
"name": "Qwen-Audio-3.0-ASR",
3+
"description": "多语种语音识别，覆盖短音频、长文件及实时流式转写，支持方言、热词与上下文增强。",
44
"items": [
55
{
66
"inferenceMetadata": {

0 commit comments

Comments
 (0)