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 ❤️

Nebius AI Studio

Nebius AI Studio provides managed inference APIs for open-weight and proprietary AI models, with developer-focused tooling for building and scaling AI applications.

DeepSeekDeepSeek V3

Nebius AI Studio offers 1 LLM API models.

Speed benchmark average: 74 tok/s.

OverviewPerformance1HealthEmbed
Avg Speed73.57 tok/s
Latency0.62 s
Updated4/29/2026
Created At12/7/2025
Website

API Endpoints

  • api.studio.nebius.ai
Healthy
Last checked 6/5/2026, 8:36:28 AM
Latency
813ms
Day
97.96%
Recent availability
Week
99.75%
Recent availability
Month
99.9%
Recent availability
Latency
845ms
7d avg: 853ms

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-0519/19100%833ms
2026-06-0453/5498.15%924ms
2026-06-0354/54100%834ms
2026-06-0259/59100%826ms
2026-06-0157/57100%876ms
2026-05-3160/60100%852ms
2026-05-3060/60100%825ms
2026-05-2959/59100%846ms
2026-05-2854/54100%889ms
2026-05-2761/61100%864ms
2026-05-2660/60100%825ms
2026-05-2561/61100%819ms
2026-05-2459/59100%810ms
2026-05-2359/59100%832ms
2026-05-2257/57100%836ms
2026-05-2159/59100%807ms
2026-05-2055/55100%821ms
2026-05-1953/53100%835ms

Recent Incidents

TimeStatus CodeLatencyError
6/4/2026, 4:06:00 PMHTTP 404—HTTP 404

Health Check Rules

  • Check target: the provider's dedicated health check URL, or its website URL as fallback.
  • Request method: HTTP GET with automatic redirect following.
  • Healthy criteria: HTTP status code 200–399 is considered healthy; any other status or network error is unhealthy.
  • Timeout: each check has a 5-second timeout. If the server does not respond within 5 s, the check is marked as failed.
  • Frequency: health checks run periodically via an automated cron job for all providers.

Data as of Apr 29, 2026, 08:24 AM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.