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 ❤️

天絮 API

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

OpenAIGPT-5.4DeepSeekDeepSeek V4 ProDeepSeekDeepSeek V4 FlashGeminiGemini 2.0 Flash 001GeminiGemini 2.0 Flash

天絮 API offers 689 LLM API models.

API pricing per token ranges from $0.0003 to $17.14/M (input).

Speed benchmark average: 93 tok/s.

天絮 API is an API aggregator, offering models from multiple vendors.

天絮 API interface preview
OverviewPerformance397Pricing689HealthEmbed
Claim this provider
星Verified by 星涵煦
Avg Speed92.67 tok/s
Latency4.38 s
Updated6/3/2026
Created At8/13/2025
Recharge Rate¥1.00 per $1 quota

Features

DrawingTaskData ExportCheck-in

API Endpoints

  • CloudFlare Route
    https://chat-api4.087654.xyz/

    Global access, primary endpoint

  • Endpoint 2
    https://tx.x.ahne.cn/
  • Endpoint 3Historical / Unverified
    https://chat-api4.087654.xyz
  • Endpoint 4Historical / Unverified
    https://chat-api.tx648.cn
  • Endpoint 5Historical / Unverified

Login Methods

GitHubLinuxDOPasskeyMicrosoft
Website
https://tx.x.ahne.cn

Data as of Jun 3, 2026, 07:08 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About 天絮 API

Health Check

100%Recent availability
History (72 pts)
PastNow

API Speed Benchmarks

ModelSpeedLatencyTests
61.40 tok/s
7.78s
5
109.48 tok/s
6.18s
10
wbot-2

API Pricing per Token

ModelAuditInput ($/M)Output ($/M)
Gemini
—FreeFree
—$0.0003$0.0003
Qwen
—$0.0014$0.0014
MetaAI

Recent Test Records

TimeModelSpeedLatency
May 2, 11:20 AM
LongCat-Flash-Lite
61.40 tok/s
7.78s
May 2, 11:18 AM
LongCat-Flash-Chat
118.05 tok/s
5.70s
May 2, 11:17 AM
LongCat-Flash-Chat
100.90 tok/s
6.67s
May 2, 11:16 AM
wbot-2
88.62 tok/s
1.72s
May 2, 11:15 AM
wbot-2-code
51.75 tok/s
1.77s
May 2, 11:13 AM
OpenAIgpt-5.4
46.34 tok/s
3.29s
May 2, 11:11 AM
DeepSeekdeepseek-v4-pro
48.13 tok/s
4.11s
May 2, 11:10 AM
DeepSeekdeepseek-v4-flash
49.02 tok/s
2.64s
May 2, 11:08 AM
OpenAIgpt-5.5
60.91 tok/s
5.31s
Sep 20, 10:07 AM
Geminigemini-2.0-flash-001
108.11 tok/s
2.70s

Announcements

warning5/3/2026

Users who have not joined the group for verification will be limited to RPM=5.

Please join the group for verification.

warning2/24/2026

Be sure to click the top right corner to view notifications (announcement cannot fit here).

88.62 tok/s
1.72s
5
wbot-2-code
51.75 tok/s
1.77s
5
OpenAIgpt-5.4
46.34 tok/s
3.29s
5
DeepSeekdeepseek-v4-pro
48.13 tok/s
4.11s
5
DeepSeekdeepseek-v4-flash
49.02 tok/s
2.64s
5
OpenAIgpt-5.5
60.91 tok/s
5.31s
5
Geminigemini-2.0-flash-001
108.11 tok/s
2.70s
5
Geminigemini-2.0-flash-exp
146.40 tok/s
4.98s
18
—
$0.0014
$0.0014
QwenQwen/Qwen3-Embedding-8B
—$0.0014$0.0014
bge-reranker-v2-m3
—$0.0014$0.0014
QwenQwen/Qwen3-Embedding-0.6B
—$0.0014$0.0014
QwenQwen/Qwen2-7B-Instruct
—$0.0014$0.0014
QwenQwen/Qwen3-Embedding-4B
—$0.0014$0.0014
dall-e-2
—$0.0029$0.014
success8/14/2025

API site is back online, everyone.

View all 397 models
LongCat-Flash-Lite
LongCat-Flash-Chat
View all 689 prices
gemini-3-flash-preview群友免费
text-embedding-004
Qwen/Qwen3-Reranker-0.6B
meta/llama-3.2-1b-instruct

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.

260 shared models

IXIOCCAPI

newapi.ixio.cc

IXIOCCAPI is a unified API gateway for large language models, providing standardized endpoints for accessing multiple AI model providers.

232 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.

189 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.

189 shared models

小豆包API

api.linkapi.org

Xiaodoubao API is a Chinese AI API relay platform hosted at api.linkapi.org, advertising low-cost and high-concurrency access to OpenAI, Claude, Gemini, Grok, Flux, and agent workflows.

188 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.

188 shared models