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 ❤️
A

AASS API

AASS API is an OpenAI-compatible API gateway built on the New API panel, exposing a unified endpoint for multiple AI models.

DeepSeekDeepSeek R1

AASS API offers 257 LLM API models.

API pricing per token ranges from $0.020 to $525.00/M (input).

Speed benchmark average: 33 tok/s.

OverviewPerformance2Pricing257HealthEmbed
Avg Speed33.14 tok/s
Latency1.19 s
Updated4/27/2026
Created At8/13/2025
Recharge Rate¥7.30 per $1 quota

Features

DrawingTaskData ExportCheck-in

Login Methods

GitHubLinuxDOWeChat
Website

API Endpoints

  • General Route
    https://api.aass.cc

    Global DCDN acceleration, suitable for all regions

  • Blank Reverse Proxy
    https://xublue.aass.cc

    Hides all front-end interfaces, focused on secondary distribution

  • International Route
    https://aimhub.nanjiren.online

    Heavily polluted, deprecated, do not use

  • Aimhub Route
    https://api.aimhub.cc

    Deprecated, do not use

About AASS API

Health Check

100%Recent availability
History (72 pts)
PastNow

API Speed Benchmarks

ModelSpeedLatencyTests
DeepSeekdeepseek-r1
33.71 tok/s
0.94s
5
ds-r1
32.57 tok/s
1.44s
5

API Pricing per Token

View all 257 prices
ModelAuditInput ($/M)Output ($/M)
dall-e-2
—$0.020$0.020
Geminigemini-2.0-flash-preview-image-generation
—$0.039$0.039
dall-e-3
—$0.040$0.040
text-embedding-3-small
—$0.140$0.140
OpenAIgpt-5-nano-2025-08-07-high
—$0.350$2.80
OpenAIgpt-5-nano-2025-08-07-low
—$0.350$2.80
OpenAIgpt-5-nano-low
—$0.350$2.80
OpenAIgpt-5-nano-medium
—$0.350$2.80
OpenAIgpt-5-nano-2025-08-07
—$0.350$2.80
OpenAIgpt-5-nano-2025-08-07-minimal
—$0.350$2.80

Recent Test Records

TimeModelSpeedLatency
Feb 14, 12:29 PM
DeepSeekdeepseek-r1
33.71 tok/s
0.94s
Feb 14, 12:11 PM
ds-r1
32.57 tok/s
1.44s

Announcements

success6/22/2025

Launch of Google Gemini's latest model family.

gemini-2.0 series and gemini-2.5 series all models.

warning6/12/2025

API requests can enable IP logging.

In version v0.8.4.0, we added the IP logging function for API requests. This function needs to be enabled by the user in 'Personal Settings - Other Settings - IP Logging'.

success6/11/2025

o3 model family adjustment.

All o3 models' prices reduced by 80%, and new model o3-pro added.

success6/10/2025

New claude4 series models added.

success6/10/2025

Welcome to use.

Welcome to use the unified large model gateway platform. Subsequent platform notifications will be updated here.

FAQ

Why does it say insufficient quota when the backend balance is sufficient?

1. Check if the token authorization quota is sufficient; it's recommended to set it to 'unlimited quota'. 2. There might be a few minutes of cache after recharging; try to ensure the API address used matches the API node accessed during recharging.

Which applications can be used?

Any application that supports binding an API key and API address (baseUrl) can basically be used; our API interface is compatible with most third-party applications.

Why can't the model answer the version number?

Because AI models are named with version numbers only after training or upgrades are completed; the model's knowledge base does not contain information about its own actual version.

What is a reverse model?

A reverse model is like a 'cracked version' of an AI model. It allows us to bypass official AI channels (such as the ChatGPT website) and use AI services directly through program interfaces. The user experience is the same as the official version. However, this 'cracked version' has a clear disadvantage - it's not stable. Because it's like 'playing hide and seek with the official side', once the official system is updated or restrictions are tightened, these cracking solutions may fail and need continuous improvement to keep working.

Similar API Providers to Compare

钱多多 API

api2.aigcbest.top

Provides AI-generated content APIs for various applications, including text and image generation.

105 shared models

Newagiai

api.newagiai.com

Provides API access to a wide range of AI models including text, image, and video generation from multiple providers.

103 shared models

小豆包API

api.linkapi.org

Xiaodoubao API is a Chinese AI API relay platform hosted at api.linkapi.org, advertising low-cost and high-concurrency access to OpenAI, Claude, Gemini, Grok, Flux, and agent workflows.

103 shared models

毫秒API

api.holdai.top

毫秒API provides a stable, high-bandwidth API forwarding service for OpenAI-compatible models, including GPT, Claude, and Midjourney, with global server deployment and transparent pricing.

103 shared models

柏拉图AI

api.bltcy.cn

柏拉图AI (api.bltcy.cn) is a multi-dimensional API integration platform providing access to over 600 AI models, serving as an alternate endpoint.

103 shared models

PoloAPI

poloai.top

An AI model API aggregation platform providing access to multiple providers including OpenAI, Claude, Gemini, and others for production environments.

100 shared models

Data as of Apr 27, 2026, 07:25 AM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.