云智API

A high-performance API aggregation platform for developers, offering diverse APIs with fast response times and multi-language SDK support.

Categories

中转站

Step 3.5 Flash Gemini 3.1 Pro GLM-Z1 Claude Opus 4.6 DeepSeek V3.2 DeepSeek R1

云智API offers 44 LLM API models.

Speed benchmark average: 70 tok/s.

云智API is an API aggregator, offering models from multiple vendors.

Avg Speed70.47 tok/s

Latency4.33 s

Total Tests120

Models9

Updated4/16/2026

Created At2/27/2026

Website

API Endpoints

yunzhiapi.cn

Supported Models

Model	Speed	Latency	Tests
Step-3.5-Flash	175.60 tok/s	6.15s	10
Mimo-v2-Flash	138.34 tok/s	1.28s	25
Gemini-3-1-Pro	80.71 tok/s	10.09s	5
GLM-Z1-0414	76.11 tok/s	10.99s	5
Ling-2.0-1T	63.22 tok/s	1.18s	5
Claude-Opus-4-6	39.01 tok/s	3.65s	5
DeepSeek-V3.2-EXP	31.16 tok/s	3.40s	55
DeepSeek3.1-Terminus	26.11 tok/s	0.51s	5
DeepSeek-R1	20.45 tok/s	21.40s	5

Available Models

35 models available (last updated: 4/18/2026)

Claude-Haiku-4-5yunzhiapiClaude-Opus-4-6yunzhiapiClaude-Sonnet-4-6yunzhiapiDeepSeek-R1yunzhi-apiDeepSeek-V3.2yunzhi-apiDeepSeek-V3.2-EXPyunzhiapiDeepSeek-V4yunzhi-apiDeepSeek3.1-TerminusyunzhiapiDouBao-Seed-1.5yunzhi-apiGLM-5.1yunzhi-apiGLM-Z1-0414yunzhi-apiGPT-5.4yunzhiapiGPT-5.4-Mediumyunzhi-apiGemini-2.5-Proyunzhi-apiGemini-3-1-ProyunzhiapiGemini-3.1-Proyunzhi-apiGemini2.5-ProyunzhiapiGpt-4.1-MiniyunzhiapiGpt5.3-CodexyunzhiapiGrok-4.1-Thinkyunzhiapi

Showing 20 of 35 models.

云智API

API Endpoints

Supported Models

Available Models

云智API

API Endpoints

Leaderboard Rankings

Supported Models

Available Models

Leaderboard Rankings