LogoLMSpeed
  • Home
  • Free
  • 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
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 ❤️
首页交流 QQ 群：1034193296，欢迎中转站站长加入讨论 AI 最热话题、newapi、openclaw 等，获取最新测速动态与反馈支持。
星见雅 API logo

星见雅 API

A large model interface gateway providing proxy access to multiple AI models with free tiers and token incentives.

Categories

Country中国Country美国中转站公益站
NvidiaNemotron 3 NanoOpenAIGPT-OSSOpenAIGPT-5.4 MiniMistralMistral Small 4GemmaGemma 3 ItMetaAILlama 3.1 InstructGeminiGemini 2.5 FlashMetaAILlama 3.2 InstructMetaAILlama 4 Maverick 128e InstructGrokGrok 4 20MinimaxMiniMax-M2.5OpenAIGPT-5.1 Codex MaxOpenAIGPT-5.4OpenAIGPT-5.3 CodexOpenAIGPT-5.2ChatGLMGlm4 7GemmaGemmaGemmaGemma 2 ItMoonshotAIKimi K2.5ChatGLMGLM-4.7OpenAIGPT-5ChatGLMGLM-4.7 FlashDeepSeekDeepSeek V3.1 TerminusChatGLMGLM-5DeepSeekDeepSeek V3.2QwenQwen3 Coder InstructChatGLMGlm5ClaudeClaude 3.5 SonnetClaudeClaude Sonnet 4.5

星见雅 API offers 314 LLM API models.

API pricing per token ranges from $0.100 to $7.50/M (input).

Speed benchmark average: 70 tok/s.

星见雅 API is an API aggregator, offering models from multiple vendors.

星见雅 API interface preview
Avg Speed69.51 tok/s
Latency6.12 s
Total Tests426
Models54
Updated4/16/2026
Created At12/21/2025
Website

API Endpoints

  • api.xinjianya.top
Claim this provider
小Verified by 小保底必歪

Supported Models

ModelSpeedLatencyTests
Nvidianvidia/nemotron-3-nano-30b-a3b
246.87 tok/s
1.15s
5
OpenAIopenai/gpt-oss-20b
227.95 tok/s
1.47s
5
OpenAICPA/gpt-5.4-mini
223.30 tok/s
3.41s
5
Mistralmistralai/mistral-small-4-119b-2603
221.17 tok/s
0.55s
5
Gemmagoogle/gemma-3-1b-it
213.18 tok/s
0.52s
10
MetaAImeta/llama-3.1-8b-instruct
200.27 tok/s
0.42s
15
Geminigemini-2.5-flash
183.01 tok/s
8.28s
5
MetaAImeta/llama-3.2-1b-instruct
149.05 tok/s
5.26s
10
OpenAI英伟达/openai/gpt-oss-120b
144.01 tok/s
0.94s
5
OpenAIopenai/gpt-oss-120b
142.72 tok/s
1.29s
10
MetaAImeta/llama-4-maverick-17b-128e-instruct
131.83 tok/s
0.48s
5
Grokgrok-4.20-0309
111.36 tok/s
1.33s
5
Minimax李/minimaxai/minimax-m2.5
104.54 tok/s
0.91s
5
MetaAImeta/llama-3.2-3b-instruct
101.40 tok/s
0.65s
5
Grokgrok-4.1-fast
99.38 tok/s
1.37s
5
Nvidia英伟达/nvidia/nemotron-3-super-120b-a12b
83.44 tok/s
5.26s
5
OpenAIgpt-5.1-codex-max
72.02 tok/s
7.98s
3
Grokgrok-4.1-thinking
65.90 tok/s
1.78s
5
Grokgrok-4.1-mini
65.28 tok/s
4.46s
10
Minimaxminimaxai/minimax-m2.5
60.04 tok/s
11.13s
15
Showing 20 of 54 models.

Available Models

260 models available (last updated: 4/16/2026)

GLM-5customGLM-5-TurbocustomGLM-5.1customMiniMax-M2.7customQwen3.6-Pluscustomdeepseek-chatdeepseekdeepseek-chat-searchcustomdeepseek-expert-chatcustomdeepseek-expert-chat-searchcustomdeepseek-expert-reasonercustomdeepseek-expert-reasoner-searchcustomdeepseek-reasonerdeepseekdeepseek-reasoner-searchcustomgpt-5.2codexgpt-5.3-codexcodexgpt-5.4codexgrok-4.20-0309customgrok-4.20-0309-non-reasoningcustomgrok-4.20-0309-reasoningcustomgrok-imagine-image-litecustom
Showing 20 of 260 models.

Leaderboard Rankings

Speed
53.9 tokens/s#67/100
Latency
0.62 s#20/100
OverviewPerformance314Pricing259Tests426HealthEmbed