LogoLMSpeed
  • Home
  • Free
  • Models
  • 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
  • Input Price
  • Output Price
  • Reasoning
  • Coding
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 ❤️

小智API

Relay

A unified API gateway for large language models, offering better pricing and stability without subscriptions.

OpenAIGPT-OSSQwenQwen3 Coder Plus

小智API offers 2 LLM API models.

Speed benchmark average: 182 tok/s.

小智API interface preview
OverviewPerformance2HealthEmbed
Avg Speed182.27 tok/s
Latency1.78 s
Updated4/27/2026
Created At12/7/2025
Website

API Endpoints

  • newai.aichat.ink
  • aifuture.pw
Unhealthy
Last checked 6/5/2026, 8:37:39 AM
Day
0%
Recent availability
Week
0%
Recent availability
Month
0%
Recent availability
Latency
—

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-050/190%—
2026-06-040/540%—
2026-06-030/540%—
2026-06-020/590%—
2026-06-010/570%—
2026-05-310/600%—
2026-05-300/600%—
2026-05-290/590%—
2026-05-280/540%—
2026-05-270/610%—
2026-05-260/600%—
2026-05-250/610%—
2026-05-240/590%—
2026-05-230/580%—
2026-05-220/570%—
2026-05-210/590%—
2026-05-200/550%—
2026-05-190/540%—

Recent Incidents

TimeStatus CodeLatencyError
6/5/2026, 8:37:39 AM——fetch failed
6/5/2026, 8:06:58 AM——fetch failed
6/5/2026, 7:36:44 AM——fetch failed
6/5/2026, 7:17:01 AM——fetch failed
6/5/2026, 6:46:57 AM——fetch failed
6/5/2026, 6:16:42 AM——fetch failed
6/5/2026, 5:46:40 AM——fetch failed
6/5/2026, 5:16:45 AM——fetch failed
6/5/2026, 4:46:47 AM——fetch failed
6/5/2026, 4:16:43 AM——fetch failed
6/5/2026, 3:56:43 AM——fetch failed
6/5/2026, 3:26:45 AM——fetch failed
6/5/2026, 2:56:48 AM——fetch failed
6/5/2026, 2:26:49 AM——fetch failed
6/5/2026, 1:56:32 AM——fetch failed
6/5/2026, 1:26:45 AM——fetch failed
6/5/2026, 12:56:34 AM——fetch failed
6/5/2026, 12:36:45 AM——fetch failed
6/5/2026, 12:16:29 AM——fetch failed
6/4/2026, 11:56:30 PM——fetch failed

Health Check Rules

  • Check target: the provider's dedicated health check URL, or its website URL as fallback.
  • Request method: HTTP GET with automatic redirect following.
  • Healthy criteria: HTTP status code 200–399 is considered healthy; any other status or network error is unhealthy.
  • Timeout: each check has a 5-second timeout. If the server does not respond within 5 s, the check is marked as failed.
  • Frequency: health checks run periodically via an automated cron job for all providers.

Data as of Apr 27, 2026, 06:10 AM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.