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 ❤️

Google Gemini API

Google Gemini API offers access to Gemini models and an OpenAI-compatible interface for application development and model inference.

GeminiGemini 3 Flash

Google Gemini API offers 1 LLM API models.

Speed benchmark average: 157 tok/s.

OverviewPerformance1HealthEmbed
Avg Speed156.97 tok/s
Latency4.02 s
Updated4/29/2026
Created At1/18/2026
Website

API Endpoints

  • generativelanguage.googleapis.com
Blocked
Last checked 6/5/2026, 11:12:13 AM
Day
—
Recent availability
Week
—
Recent availability
Month
—
Recent availability
Latency
—

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-050/25——
2026-06-040/53——
2026-06-030/54——
2026-06-020/59——
2026-06-010/57——
2026-05-310/60——
2026-05-300/60——
2026-05-290/59——
2026-05-280/54——
2026-05-270/61——
2026-05-260/60——
2026-05-250/60——
2026-05-240/59——
2026-05-230/56——
2026-05-220/57——
2026-05-210/59——
2026-05-200/55——
2026-05-190/52——

Recent Incidents

No incidents reported recently

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, 08:45 AM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.