LogoLMSpeed
  • Home
  • Free
  • Categories
  • Models
  • Docs
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2025 LMSpeed All Rights Reserved.
BACK TO INDEX
A

New API

Website
Updated 12/7/2025
New API interface preview
Performance Stats
Avg Speed
29.88t/s
Latency
2.11s
Total Tests
55
Models
2

About New API

A unified API gateway for accessing multiple large language models and AI services through standardized endpoints.

DeepSeekDeepSeek-V3

New API provides a unified gateway for accessing various large language models and AI services. It supports over 30 providers, including MoonshotAI, OpenAI, Grok, Zhipu, Volcengine, Cohere, Claude, Gemini, Suno, Minimax, Wenxin, Spark, Qingyan, DeepSeek, Qwen, Midjourney, AzureAI, Hunyuan, and Xinference. Key endpoints include /v1/chat/completions, /v1/embeddings, /v1/images/generations, /v1/audio/transcriptions, and /v1beta/models. The service offers better pricing and stability without subscription requirements, allowing users to replace model base URLs with its endpoints. Typical use cases involve integrating AI capabilities like text generation, embeddings, image creation, and audio processing into applications.

Supported Models

ModelSpeedLatencyTests
deepseek-ai/DeepSeek-V3-0324
38.25 t/s
1.91s
25
deepseek-ai/DeepSeek-V3
22.90 t/s
2.28s
30

Recent Test Records

TimeModelSpeedLatency
Aug 29, 10:20 AMdeepseek-ai/DeepSeek-V3-0324
37.00 t/s
2.02s
Aug 29, 10:18 AMdeepseek-ai/DeepSeek-V3-0324
39.29 t/s
2.08s
Aug 29, 10:16 AMdeepseek-ai/DeepSeek-V3-0324
37.20 t/s
2.09s
Aug 29, 10:14 AMdeepseek-ai/DeepSeek-V3-0324
38.87 t/s
1.84s
Aug 29, 10:12 AMdeepseek-ai/DeepSeek-V3-0324
38.89 t/s
1.54s
Jul 23, 07:42 AMdeepseek-ai/DeepSeek-V3
22.07 t/s
2.49s
Jul 23, 07:39 AMdeepseek-ai/DeepSeek-V3
22.02 t/s
2.04s
Jul 23, 07:36 AMdeepseek-ai/DeepSeek-V3
21.94 t/s
2.09s
Jul 20, 07:45 AMdeepseek-ai/DeepSeek-V3
22.86 t/s
3.21s
Jul 20, 07:42 AMdeepseek-ai/DeepSeek-V3
24.53 t/s
1.75s