New API offers a unified gateway for accessing various large language models and AI services through standardized endpoints. The service supports models from providers including MoonshotAI, OpenAI, Grok, Zhipu, Volcengine, Cohere, Claude, Gemini, Suno, Minimax, Wenxin, Spark, Qingyan, DeepSeek, Qwen, Midjourney, AzureAI, Hunyuan, and Xinference.

Key endpoints include:

/v1/chat/completions for chat completions
/v1/embeddings for embedding generation
/v1/rerank for reranking functionality
/v1/images/generations, /v1/images/edits, and /v1/images/variations for image generation and manipulation
/v1/audio/speech, /v1/audio/transcriptions, and /v1/audio/translations for audio processing
/v1beta/models for model information

The platform emphasizes better pricing and stability compared to direct provider access, with no subscription requirements. Users can integrate by replacing their model BASE URL with the provided endpoints. Typical use cases include AI-powered applications requiring multiple model types, developers seeking simplified API management across providers, and projects needing cost-effective access to various AI capabilities.

Model

Input ($/M)

Output ($/M)

Audit

Speed

Latency

翻译

—

60.5 t/s

0.97 s

deepseek-ai/deepseek-vl2

—

125.8 t/s

0.75 s

free:QwQ-32B

—

27.7 t/s

26.13 s

internlm/internlm2_5-20b-chat

—

61.8 t/s

0.77 s

Pro/Qwen/Qwen2-1.5B-Instruct

—

204.0 t/s

0.60 s

Pro/Qwen/Qwen2-VL-7B-Instruct

—

93.2 t/s

0.71 s

Pro/Qwen/Qwen2.5-7B-Instruct

—

20.7 t/s

0.87 s

Pro/Qwen/Qwen2.5-VL-7B-Instruct

—

85.5 t/s

0.76 s

Qwen/QVQ-72B-Preview

—

31.2 t/s

0.99 s

Qwen/Qwen2-1.5B-Instruct

—

213.8 t/s

0.67 s

Qwen/Qwen2-7B-Instruct

—

83.9 t/s

0.59 s

Qwen/Qwen2-VL-72B-Instruct

—

28.5 t/s

0.78 s

Qwen/Qwen2.5-14B-Instruct

—

71.2 t/s

0.65 s

Qwen/Qwen2.5-32B-Instruct

—

58.6 t/s

0.73 s

Qwen/Qwen2.5-VL-32B-Instruct

—

30.1 t/s

0.87 s

Qwen/QwQ-32B-Preview

—

71.1 t/s

0.74 s

THUDM/chatglm3-6b

—

32.2 t/s

0.74 s

免费DS-VL2

—

86.8 t/s

1.86 s

免费GLM-4-9B-128K

—

73.7 t/s

0.77 s

免费Grok3

—

85.5 t/s

1.39 s

免费Grok3-mini

—

180.9 t/s

3.99 s

免费Qwen2-1.5B

—

203.4 t/s

0.68 s

免费Qwen2-7B

—

93.0 t/s

0.85 s

免费Qwen2-VL-7B

—

77.8 t/s

0.95 s

免费Qwen2.5-14B

—

78.0 t/s

0.69 s

免费Qwen2.5-VL-7B

—

63.6 t/s

1.03 s

免费V3-0324

—

24.4 t/s

1.60 s

官方R1

—

19.3 t/s

53.05 s

沉浸式翻译

—

72.2 t/s

1.01 s

火山R1

—

33.9 t/s

22.23 s

火山R1-32B

—

39.3 t/s

22.59 s

火山V3

—

38.8 t/s

1.26 s

硅基-R1

—

21.4 t/s

41.74 s

硅基-付费-Pro-R1

—

25.5 t/s

29.06 s

Time

Model

Speed

Latency

Feb 15, 03:21 AM

翻译

60.49 tok/s

0.97s

Oct 18, 10:08 PM

free:QwQ-32B

29.86 tok/s

26.88s

Oct 18, 04:42 AM

free:QwQ-32B

26.86 tok/s

18.40s

Oct 17, 01:01 PM

free:QwQ-32B

25.67 tok/s

34.23s

Oct 17, 07:35 AM

free:QwQ-32B

32.87 tok/s

21.62s

Oct 16, 10:53 AM

free:QwQ-32B

30.19 tok/s

10.72s

Oct 16, 07:43 AM

free:QwQ-32B

35.74 tok/s

23.83s

Oct 14, 01:52 PM

free:QwQ-32B

33.15 tok/s

5.87s

Oct 14, 03:29 AM

free:QwQ-32B

10.21 tok/s

7.05s

Oct 14, 03:22 AM

free:QwQ-32B

23.06 tok/s

32.75s

Provider

Why compare

Models

Free

Avg price

Speed

30d uptime

联无所AI

lianwusuoai

联无所AI provides an OpenAI-compatible API relay service for accessing multiple AI models with competitive pricing.

Current provider baseline

N/A

29 tok/s

0.7%

CaMeL AI

api-kr777-top

CaMeL AI provides an OpenAI-compatible API gateway with extensive model coverage and pricing options.

Faster measured speed
Higher 30-day availability
More free-model options
Broader model coverage

194

$88.30/M

93 tok/s

99%

api-vectorengine-ai

Vector Engine provides an API platform aggregating access to over 500 AI large models with OpenAI API compatibility and global deployment.

Faster measured speed
Higher 30-day availability
More free-model options
Broader model coverage

182

$5.75/M

89 tok/s

99.6%

api-n1n-ai

N1N provides API access to a wide range of AI models including GPT-4, Claude 3, Gemini, and others for text, image, and video generation.

Faster measured speed
Higher 30-day availability
More free-model options
Broader model coverage

177

$8.65/M

90 tok/s

99.7%

180txt-cn

180txt API provides an OpenAI-compatible API relay for multiple AI models.

Faster measured speed
Higher 30-day availability
More free-model options
Broader model coverage

$18.03/M

42 tok/s

0.7%

api-futureppo-top

Future Hub is a large-scale OpenAI-compatible API gateway at api.futureppo.top with extensive model coverage and pricing data.

Faster measured speed
More free-model options
Broader model coverage

132

223

N/A

263 tok/s

0.6%

stark-gpt-load-onrender-com

An OpenAI-compatible API relay hosted on Render, providing access to multiple AI models.

Faster measured speed
Higher 30-day availability
Broader model coverage

N/A

45 tok/s

96.4%

Notes

Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 5-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.

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.

联无所AI

联无所AI

API Endpoints

Health Check

API Benchmarks & Pricing

Recent Test Records

Similar API Provider Alternatives to Compare

Notes

Similar API Provider Alternatives to Compare

Provider	Why compare	Models	Free	Avg price	Speed	30d uptime
联无所AI lianwusuoai 联无所AI provides an OpenAI-compatible API relay service for accessing multiple AI models with competitive pricing.	Current provider baseline	17	0	N/A	29 tok/s	0.7%
CaMeL AI api-kr777-top CaMeL AI provides an OpenAI-compatible API gateway with extensive model coverage and pricing options.	Faster measured speed Higher 30-day availability More free-model options Broader model coverage	194	4	$88.30/M	93 tok/s	99%
api-vectorengine-ai Vector Engine provides an API platform aggregating access to over 500 AI large models with OpenAI API compatibility and global deployment.	Faster measured speed Higher 30-day availability More free-model options Broader model coverage	182	6	$5.75/M	89 tok/s	99.6%
api-n1n-ai N1N provides API access to a wide range of AI models including GPT-4, Claude 3, Gemini, and others for text, image, and video generation.	Faster measured speed Higher 30-day availability More free-model options Broader model coverage	177	6	$8.65/M	90 tok/s	99.7%
180txt-cn 180txt API provides an OpenAI-compatible API relay for multiple AI models.	Faster measured speed Higher 30-day availability More free-model options Broader model coverage	37	77	$18.03/M	42 tok/s	0.7%
api-futureppo-top Future Hub is a large-scale OpenAI-compatible API gateway at api.futureppo.top with extensive model coverage and pricing data.	Faster measured speed More free-model options Broader model coverage	132	223	N/A	263 tok/s	0.6%
stark-gpt-load-onrender-com An OpenAI-compatible API relay hosted on Render, providing access to multiple AI models.	Faster measured speed Higher 30-day availability Broader model coverage	29	0	N/A	45 tok/s	96.4%

联无所AI

联无所AI

API Endpoints

About 联无所AI

Health Check

API Benchmarks & Pricing

Recent Test Records

Similar API Provider Alternatives to Compare

Notes

Similar API Provider Alternatives to Compare