LogoLMSpeed
  • Home
  • Free
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️
首页交流 QQ 群：1034193296，欢迎中转站站长加入讨论 AI 最热话题、newapi、openclaw 等，获取最新测速动态与反馈支持。
算了么 API logo

算了么 API

Provides OpenAI-compatible API access to open-source AI models like DeepSeek and QwQ, powered by shared idle computing resources.

DeepSeekDeepSeek R1QwenQwen3 VL ThinkingChatGLMGLM-4 FlashChatGLMGLM-4.5

算了么 API offers 16 LLM API models.

Speed benchmark average: 25 tok/s.

算了么 API interface preview
Avg Speed24.60 tok/s
Latency24.93 s
Total Tests13580
Models9
Updated4/18/2026
Created At8/13/2025
Online SinceApr 16, 2026, 02:23 AM

Features

TaskData Export
Website

API Endpoints

  • Historical / Unverified
    https://api.suanli.cn

Supported Models

ModelSpeedLatencyTests
best-free
101.41 tok/s
17.62s
10
DeepSeekdeepseek-r1:7b
46.77 tok/s
5.66s
385
QwenQwen/QwQ-32B
45.16 tok/s
20.80s
65
QwenQwen/Qwen3-VL-32B-Thinking
38.81 tok/s
19.77s
69
ChatGLMzhipu/glm-4-flash
35.00 tok/s
1.78s
10
QwQ-32B
28.31 tok/s
2.66s
45
free:QwQ-32B
27.71 tok/s
26.05s
6449
ChatGLMzai-org/GLM-4.5
20.72 tok/s
1.47s
5
Qwenfree:Qwen3-30B-A3B
19.73 tok/s
25.26s
6542

Available Models

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

Qwen/QwQ-32BcustomQwen/Qwen3-VL-32B-Thinkingcustomdeepseek-r1:7bcustomfree:QwQ-32Bcustomfree:Qwen3-30B-A3Bcustomfree:Qwen3.5-9Bcustomzai-org/GLM-4.5custom

Leaderboard Rankings

Speed
52.4 tokens/s#71/100
OverviewPerformance16Pricing5Tests13580HealthEmbed