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 ❤️
T

MKE AI

Relay

MKE AI is an OpenAI-compatible API relay offering access to multiple AI models with competitive pricing and high availability.

DeepSeekDeepSeek V4 Pro

MKE AI offers 29 LLM API models.

API pricing per token ranges from $0.050 to $12.00/M (input).

Speed benchmark average: 33 tok/s.

MKE AI interface preview
OverviewPerformance29Pricing21HealthEmbed
Avg Speed32.55 tok/s
Latency7.44 s
Updated4/27/2026
Created At8/13/2025
Recharge Rate¥1.00 per $1 quota

Features

TaskData Export
Website

API Endpoints

  • Endpoint 1Historical / Unverified
    https://tb.api.mkeai.com

Supported Models

ModelSpeedLatencyTests
DeepSeekdeepseek-v4-pro
32.55 tok/s
7.44s
5

Available Models

28 models available (last updated: 5/31/2026)

Qwen/Qwen3-Embedding-0.6BsiliconflowQwen/Qwen3-Embedding-4BsiliconflowQwen/Qwen3-Embedding-8Bsiliconflowdeepseek-chatdeepseekdeepseek-ocrsiliconflowdeepseek-r1cozedeepseek-r1-0528customdeepseek-reasonerdeepseekdeepseek-v3openaideepseek-v3-0324openaideepseek-v3.1openaideepseek-v3.1-thinkingopenaideepseek-v3.2openaideepseek-v3.2-expopenaideepseek-v3.2-thinkingopenaideepseek-v4-flashdeepseekdeepseek-v4-prodeepseekgemini-2.5-flash-imagegoogle geminigemini-2.5-flash-image-previewgoogle geminigemini-2.5-progoogle gemini
Showing 20 of 28 models.

Data as of Apr 27, 2026, 07:26 AM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

Leaderboard Rankings

Health
100.0%#56/100