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
  • Model Pricing
  • Model Speed
  • 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 ❤️

PackyAPI

codex-api.packycode.com

LMSpeed tracks PackyAPI API pricing, model coverage, speed tests, and uptime signals for codex-api.packycode.com.

PackyAPI (codex-api.packycode.com) is an OpenAI-compatible API relay for Codex and other models via a single interface.

ClaudeClaude Opus 4.7OpenAIGPT-5.2

PackyAPI offers 48 LLM API models.

API pricing per token ranges from $0.0014 to $8.57/M (input).

Speed benchmark average: 78 tok/s.

PackyAPI interface preview
OverviewPerformance10Pricing48HealthEmbed
Avg Speed77.79 tok/s
Latency8.40 s
Updated6/8/2026
Created At1/5/2026
Recharge Rate¥1.00 per $1 quota

Features

DrawingTaskData Export

Login Methods

API Endpoints

  • Main Endpoint
    https://www.packyapi.com

    Stable and reliable, suitable for production environments

  • Optimized Route Endpoint
    https://api-slb.packyapi.com

    Optimized route, suitable for latency-sensitive scenarios

  • Endpoint 3Historical / Unverified
    https://codex-api.packycode.com
  • Endpoint 4Historical / Unverified
    https://codex-api-slb.packycode.com
Healthy
Last checked 6/9/2026, 5:41:21 AM
Latency
286ms
Day
100%
Recent availability
Week
100%
Recent availability
Month
100%
Recent availability
Latency
316ms
7d avg: 312ms

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-0915/15100%285ms
2026-06-0858/58100%333ms
2026-06-0757/57100%314ms
2026-06-0654/54100%305ms
2026-06-0555/55100%329ms
2026-06-0453/53100%319ms
2026-06-0354/54100%291ms
2026-06-0259/59100%321ms
2026-06-0157/57100%321ms
2026-05-3160/60100%301ms
2026-05-3060/60100%294ms
2026-05-2959/59100%336ms
2026-05-2854/54100%277ms
2026-05-2761/61100%292ms
2026-05-2660/60100%322ms
2026-05-2560/60100%280ms
2026-05-2459/59100%267ms
2026-05-2356/56100%290ms
2026-05-229/9100%261ms

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.
OIDC
Website

Data as of Jun 8, 2026, 06:22 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

Leaderboard Rankings

Health
100.0%#18/100