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 ❤️

鲨鱼魔法

鲨鱼魔法 (sharkmagic.top) provides access to official paid AI models like Gemini, Claude, and GPT through a unified proxy with OpenAI-compatible API.

DeepSeekDeepSeek R1GrokGrok-3ClaudeClaude Sonnet 4

鲨鱼魔法 offers 876 LLM API models.

API pricing per token ranges from $2.00 to $93750.00/M (input).

Speed benchmark average: 73 tok/s.

鲨鱼魔法 interface preview
OverviewPerformance6Pricing876HealthEmbed
Avg Speed72.51 tok/s
Latency5.36 s
Updated5/13/2026
Created At1/11/2026
Recharge Rate¥0.01 per $1 quota

Features

DrawingTaskData Export
Website

API Endpoints

  • Server Node
    https://openai.sharkmagic.top/

    API main site

  • Tutorial Documentation
    https://ucn3ufumwvhb.feishu.cn/wiki/SCqmwi5OriSL9RkxDhwc1pb0nxh

    View documentation

  • KOL Promotion Platform
    https://kol.sharkmagic.com.cn/

    Earn referral rewards up to 25% commission

  • Immortal Journey
    https://ddct.sharkmagic.com.cn/

    AI game

  • Endpoint 5Historical / Unverified
    https://openai.sharkmagic.top
  • Endpoint 6Historical / Unverified

About 鲨鱼魔法

Health Check

100%Recent availability
History (72 pts)
PastNow

API Speed Benchmarks

ModelSpeedLatencyTests
DeepSeekdeepseek-r1
56.00 tok/s
1.50s
5
Grokgrok-3
38.91 tok/s
2.64s
25
Claudeclaude-4-sonnet
36.44 tok/s
6.23s
15
Gemini[503]gemini-flash-lite
229.64 tok/s
2.17s
5
Gemini[503]gemini-flash
199.70 tok/s
10.04s
5
Gemini[503]gemini-pro
82.99 tok/s
22.12s
4

API Pricing per Token

View all 876 prices
ModelAuditInput ($/M)Output ($/M)
Gemini[hm]q|gemini-2.5-flash
—$2.00$2.00
Gemini[hm]q|gemini-2.5-flash-search
—$2.00$2.00
Gemini[ba]q|假流式/gemini-2.5-flash-search
—$2.00$2.00
Gemini[hm]q|cli/gemini-2.5-flash-search
—$2.00$2.00
Gemini[hm]q|gemini-2.5-flash-maxthinking-search
—$2.00$2.00
Gemini[ba]q|假流式/gemini-2.5-flash-maxthinking-search
—$2.00$2.00
Gemini[hm]q|cli/gemini-2.5-flash-nothinking
—$2.00$2.00
Gemini[ba]q|假流式/gemini-2.5-flash-nothinking-search
—$2.00$2.00
Gemini[ba]q|gemini-2.5-flash-nothinking-search
—$2.00$2.00
Gemini[hm]q|gemini-2.5-flash-maxthinking
—$2.00$2.00

Recent Test Records

TimeModelSpeedLatency
Dec 15, 12:49 PM
DeepSeekdeepseek-r1
56.00 tok/s
1.50s
Aug 12, 02:48 PM
Grokgrok-3
28.05 tok/s
6.44s
Aug 12, 02:47 PM
Claudeclaude-4-sonnet
50.48 tok/s
3.47s
Aug 12, 02:25 PM
Gemini[503]gemini-flash-lite
229.64 tok/s
2.17s
Aug 12, 02:23 PM
Gemini[503]gemini-flash
199.70 tok/s
10.04s
Aug 12, 02:20 PM
Gemini[503]gemini-pro
82.99 tok/s
22.12s
Jul 23, 04:20 PM
Grokgrok-3
23.68 tok/s
1.58s
Jun 16, 05:39 AM
Claudeclaude-4-sonnet
31.73 tok/s
7.93s
Jun 16, 04:48 AM
Claudeclaude-4-sonnet
27.10 tok/s
7.28s
Mar 27, 09:45 AM
Grokgrok-3
49.76 tok/s
1.90s

Announcements

default12/19/2025

Platform sign-in system in beta, daily sign-in to earn points, points can be exchanged for various rewards, come check it out in the after-sales group on the homepage~

success12/11/2025

Due to force majeure, the platform will switch to a new address. This address (with .com.cn suffix. If you entered from .top suffix, ignore this announcement.) will be discontinued in 7 days. Please add the after-sales group promptly to get the latest address.

Old server shutdown completed.

default11/26/2025

The platform is distributing Cloud Tavern for free, come claim it in the after-sales group~

default11/21/2025

Starting now, anyone who has accumulated a certain amount of consumption on the platform can claim a free Cloud Tavern monthly card in the after-sales group, chat anytime, anywhere, click on the after-sales group on the homepage to enjoy~

warning11/8/2025

Recently, Google's risk control is strict. If you don't know which model is available, you can check in the after-sales group. The after-sales group number is on the platform homepage or in the announcements.

warning10/14/2025

Recently, due to Google restrictions, model fluctuations are significant. For the specific status of models, please check the after-sales group. Thank you~

After-sales group is on the homepage or in the announcements.

error9/14/2025

The practice arena currently has a critical bug. It should have been closed directly, but due to feedback from some users who have this need, it has been reopened. This bug will cause calls in the practice arena to deduct not only the remaining quota but also the quota limit (with no logs). Please do not continue using the practice arena. If you continue to use it, you are deemed to agree to bear the consequences, and we will not provide compensation. Thank you for your understanding.

default9/12/2025

Weekly maintenance announcement: Dear users, the platform will begin weekly update maintenance on September 14th at 10:00 AM. The estimated downtime is 1 hour. Please try to avoid sensitive operations during this time. Thank you for your support~

default9/6/2025

Please add the after-sales group mentioned in the announcements or on the homepage promptly to avoid missing important notices. Future announcements will only be notified within the group.

ongoing9/5/2025

Weekly maintenance announcement: Dear users, the platform will begin weekly update maintenance on September 6th at 10:00 AM. The estimated downtime is 1 hour. Please try to avoid sensitive operations during this time. Thank you for your support~

default8/27/2025

Models without prefix changed to official self, just modify the model name directly.

success8/26/2025

Limited-time event launched! Volcano Doubao models, all 50% off! Valid until September 4th (excluding 1.6-think model)

default8/22/2025

Weekly maintenance announcement The platform will begin weekly update maintenance on August 24th at 10:00 AM. The estimated maintenance time is 30 minutes. Please try to avoid sensitive operations during this time. Thank you for your support~

default8/20/2025

Platform update, Volcano official models, all 30% off except v3!!! Official channel quality guaranteed.

ongoing8/20/2025

Hello users, in order to unify the platform's model naming conventions, the platform will standardize model naming tonight. You may need to re-copy and configure the interface modelId to continue using it. Thank you for your long-term support.

default8/17/2025

The prices of most models on the platform will be kept as stable as possible, but occasionally adjustments may be needed due to channel or official model price changes. Notifications will be given in the after-sales group at that time. Therefore, please add the after-sales group promptly for better service. Thank you.

warning8/16/2025

Based on statistical analysis, the estimated availability time for the gemini-2.5-pro model is: Beijing Time (UTC+8): 2:00 - 15:00, Coordinated Universal Time (UTC): 18:00 - 7:00. (Statistical data may have errors, please refer to actual conditions.)

success8/15/2025

Weekly maintenance announcement The platform will begin weekly update maintenance on August 16th at 10:00 AM. The estimated maintenance time is 30 minutes. Please try to avoid sensitive operations during this time. Thank you for your support~

Completed

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.

64 shared models

V-API

api.gpt.ge

Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.

64 shared models

AAAI

api.aaai.vip

API provider for AI services accessible via dedicated endpoints.

63 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.

61 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.

61 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.

61 shared models
https://openai.sharkmagic.online
  • Endpoint 7Historical / Unverified
    https://openai.sharkmagic.com.cn
  • Endpoint 8Historical / Unverified
    https://st.sharkmagic.top
  • Endpoint 9Historical / Unverified
    https://ucn3ufumwvhb.feishu.cn
  • Endpoint 10Historical / Unverified
    https://kol.sharkmagic.com.cn
  • Endpoint 11Historical / Unverified
    https://ddct.sharkmagic.com.cn
  • Endpoint 12Historical / Unverified
    https://nai.sharkmagic.com.cn
  • Endpoint 13Historical / Unverified
    https://stol.sharkmagic.top
  • Data as of May 13, 2026, 04:02 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.