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
New API logo

New API

Website
Updated 12/8/2025
New API interface preview
Performance Stats
Avg Speed
181.98t/s
Latency
0.88s
Total Tests
20
Models
4

About New API

A unified API gateway providing access to multiple large language models and AI services through standardized endpoints.

QwenQwen3

New API is a unified API gateway that aggregates access to various large language models and AI services. It supports over 30 providers including OpenAI, Claude, Gemini, Grok, MoonshotAI, Zhipu, DeepSeek, Qwen, and Midjourney. The service offers standardized endpoints compatible with common AI API formats, allowing users to switch between different models by changing the base URL. Key endpoints include /v1/chat/completions, /v1/embeddings, /v1/images/generations, /v1/audio/transcriptions, and /v1beta/models. The platform emphasizes competitive pricing and stability without subscription requirements, operating in a self-use mode. Typical use cases include chat completions, text embeddings, image generation and editing, audio processing, and accessing multiple AI models through a single interface.

Supported Models

ModelSpeedLatencyTests
allam-2-7b
337.15 t/s
0.27s
5
gemini-2.5-flash-lite-ts
214.83 t/s
1.17s
5
lgai/exaone-3-5-32b-instruct
100.84 t/s
1.08s
5
Qwen/Qwen3-32B-FP8
75.12 t/s
1.01s
5

Recent Test Records

TimeModelSpeedLatency
Aug 9, 08:16 AMgemini-2.5-flash-lite-ts
214.83 t/s
1.17s
Aug 9, 08:14 AMlgai/exaone-3-5-32b-instruct
100.84 t/s
1.08s
Aug 9, 08:11 AMQwen/Qwen3-32B-FP8
75.12 t/s
1.01s
Aug 9, 08:10 AMallam-2-7b
337.15 t/s
0.27s