Sponsored byFusecodeEnterprise coding API for Claude Code, Codex, and model workflows.
LogoLMSpeed
  • Free
  • Models
  • Providers
  • Docs
LogoLMSpeed
  1. Home
  2. Providers
  3. AI Dext Top
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
Tools
  • Speed Test
  • Provider Audit
Resources
  • Provider Directory
  • Documentation
  • GEO Checker
  • Viora
  • Botab
  • VidBee
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️

Dext API

ai.dext.top
🇨🇳CountryChinaRelay
Models
551 models
From
--
Speed
19 tok/s
Updated
7/9/2026

Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage.

OverviewHealthBenchmarks551Tests5Alternatives
Latency28.79 s
Created At5/28/2026
Recharge Rate¥1.00 per $1 quota

Features

DrawingTaskData Export

Login Methods

Passkey
Website
Claim this provider
DVerified by dext-stu

API Endpoints

  • Endpoint 1
    https://dext.lynseq.com/
  • Endpoint 2
    https://ai.dext.top/
  • Endpoint 3Historical / Unverified
    https://ai.dext.top
  • Endpoint 4Historical / Unverified
    https://dext.lynseq.com

Notes

  • Health checks: 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.
  • Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
  • Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.

Data as of Jul 9, 2026, 07:04 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

Health Check

100%Recent availability
API connectivity
Healthy
Latency: 868ms
Model availability
Skipped
0/0 No probe key
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 11 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

View all 10 modelsView all 551 prices
ModelInput ($/M)Output ($/M)AuditSpeedLatency
Gemini
gemini-3.1-flash-imageauto
$75.00/M$300.00/M———
Gemini
google/gemini-3.1-flash-imageauto
$0.500/M$3.00/M———
Gemini
google/gemini-3.1-flash-image-previewauto
$0.500/M$3.00/M———
Gemini
google/gemini-3-pro-imageauto
$2.00/M$12.00/M———
Gemini
google/gemini-3-pro-image-previewauto
$2.00/M$12.00/M———
ChatGLM
glm-5.2auto
$0.500/M$2.20/M———
ChatGLM
z-ai/glm-5.2auto
$1.00/M$4.00/M———
MoonshotAI
kimi-k2.7-codeauto
$0.550/M$2.25/M———
Claude
claude-fable-5auto
$10.00/M$50.00/M———
Claude
anthropic/claude-opus-4.8auto
$5.00/M$25.01/M———
Claude
claude-opus-4-7
--591008610018.9 t/s28.79 s

Showing 11 of 11 model rows

Recent Test Records

TimeModelSpeedLatency
May 28, 05:02 PM
Claudeclaude-opus-4-7
18.85 tok/s
28.79s

Similar API Provider Alternatives to Compare

Compare Dext API alternatives against 6 nearby API providers using 972 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
Dext API

ai-dext-top

Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage.

Current provider baseline272551N/A19 tok/s100%
天絮 API

tianxu-api

Tianxu API provides an AI model relay service with multiple access points and stable connectivity.

  • Faster measured speed
  • Broader model coverage
  • Same provider category
345145N/A93 tok/s75%

ai-071129-xyz

MapleLeaf API runs a New API-powered gateway on ai.071129.xyz for aggregated access to multiple AI models.

  • Faster measured speed
  • Same provider category
262292N/A38 tok/s75%

llm-whitedream-top

RenRen API runs a New API-powered gateway on llm.whitedream.top for aggregated access to multiple AI models.

  • Faster measured speed
  • Same provider category
25779N/A271 tok/s75%

ai-chuyel-top

A free, community-supported API service providing access to various AI models for developers and users.

  • Faster measured speed
  • Same provider category
223461N/A171 tok/s75%

91vip-futureppo-top

91VIP is a non-profit API service providing access to various AI models including Codex, Claude Code, and Open Code, with specific unlimited-use groups.

  • Faster measured speed
  • Same provider category
215181N/A318 tok/s75%

api-xinjianya-top

Xinjianya API is an OpenAI-compatible API relay at api.xinjianya.top. Service availability may be limited.

  • Faster measured speed
  • Same provider category
188211N/A67 tok/s75%
MapleLeaf API
RenRen API
初叶🍂Furry API
91VIP
星见雅 API