A unified API gateway providing access to multiple large language models with direct connectivity in China.

Models
752 models
From
$0.0005/M
Speed
111 tok/s
Updated
6/8/2026
Latency
0.00 s
Created At
8/13/2025
Recharge Rate
¥0.50 per $1 quota

Features

DrawingTaskData ExportCheck-in

Login Methods

GitHubLinuxDO

API Endpoints

  • Main Site
    https://yunwu.ai

    US high-defense load balancing site cluster

  • CF Site
    https://api.apiplus.org

    Global CDN, average domestic access speed

  • No-Login Page API Interface
    https://api.zhongzhuan.chat

    Convenient for reselling KEYs

  • Domestic Server
    https://api3.wlai.vip

    Domestic high-defense server line

  • Endpoint 5Historical / Unverified
    https://yunwu.zeabur.app
Claim this provider

Verify ownership to unlock provider management features:

  • Edit provider name, content, and links
  • Get featured with priority traffic and visibility boost
  • Display a verified badge to build user trust

Leaderboard Rankings

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About YUNWU API

YUNWU API is a unified LLM API gateway that offers stable and reliable API relay services. It supports a wide range of AI models, including ChatGPT, Claude, Gemini, Grok, MoonshotAI, Zhipu, and over 30 others from providers like OpenAI, Cohere, and DeepSeek. Key features include direct connectivity within China without requiring a proxy, low latency, high concurrency, and pay-as-you-go pricing. The service is designed for applications needing access to multiple LLMs through a single interface, with common integrations for tools like LobeChat and OpenCat.

Health Check

100%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 5391 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
doubao-1-5-pro-256k-250115测试
$3.42/M$6.16/M
doubao-1-5-pro-32k-character-250228测试
$0.548/M$1.37/M
doubao-seed-1-6-flash-250615测试
$0.205/M$2.05/M
doubao-seed-1-6-flash-250715测试
$0.205/M$2.05/M
mj_uploads测试
$0.0021/request-
omni_flash-10s测试
$1.78/request-
text-embedding-v1测试
$0.068/M$0.068/M
gpt-5.6-luna-2026-07-09
--
gpt-5.6-sol-2026-07-09
--
gpt-5.6-terra-2026-07-09
--
gpt-5.5-openai-compact
--
$0.342/M$1.71/M
claude-opus-5特价 Claude Code
$0.411/M$2.05/M
claude-opus-5Claude独立特供
$0.822/M$4.11/M
claude-opus-5Claude Code专属
$0.822/M$4.11/M
$1.37/M$6.85/M
claude-opus-5huawei-cc
$1.89/M$9.45/M
claude-opus-5huawei-ccmax
$1.89/M$9.45/M
$2.05/M$10.27/M
claude-opus-5官转克劳德2
$2.05/M$10.27/M
claude-opus-5inferel special supply
$2.74/M$13.70/M
claude-opus-5特供-awsclaude
$2.74/M$13.70/M
$3.42/M$17.12/M
claude-opus-5官转克劳德3
$4.11/M$20.55/M
$0.103/M$0.514/M

Showing 25 of 5391 model rows

Recent Test Records

TimeModelSpeedLatency
Jul 29, 10:56 PM
gpt-5.6-sol
53.00 tok/s
2.27s
Jul 26, 08:49 PM
gpt-5.6-sol
53.42 tok/s
2.06s
Jul 4, 04:15 PM
claude-opus-4-7
162.36 tok/s
1.91s
May 15, 04:00 PM
gpt-5-mini
82.67 tok/s
6.57s
Apr 24, 11:02 AM
gpt-5.4-nano
19.82 tok/s
7.05s
Apr 24, 11:00 AM
deepseek-v4-flash
67.17 tok/s
2.68s
Apr 24, 05:00 AM
deepseek-v4-flash
80.40 tok/s
2.96s
Apr 1, 11:04 AM
gpt-5-nano-2025-08-07
111.99 tok/s
10.26s
Apr 1, 11:00 AM
gpt-5-nano
91.01 tok/s
14.07s
Mar 26, 05:04 AM
gpt-5.4-mini
200.70 tok/s
1.44s

Similar API Provider Alternatives to Compare

Compare YUNWU API alternatives against 6 nearby API providers using 1099 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
YUNWU API

yunwu-ai

A unified API gateway providing access to multiple large language models with direct connectivity in China.

Current provider baseline7522$0.0005/M111 tok/s9980%
91VIP API

hcg-pippi-top

A unified API gateway providing access to multiple large language models and AI services with competitive pricing and stability.

  • Faster measured speed
  • More free-model options
18130$0.467/M148 tok/s9890%
钱多多 API

api2-aigcbest-top

Provides AI-generated content APIs for various applications, including text and image generation.

  • Broader model coverage
1,4182$0.0025/M101 tok/s9940%
向量引擎

api-vectorengine-ai

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

  • Broader model coverage
8052$0.0005/M89 tok/s9970%
Koyeb AI Gateway

new-api-koyeb-app

An OpenAI-compatible API gateway deployed on Koyeb, providing access to multiple AI models.

  • More free-model options
578420N/A33 tok/s9960%
艾可API

aicanapi-com

AicanAPI provides an enterprise-grade API management platform with high-performance architecture, security compliance, and cost optimization for business digital transformation.

  • More free-model options
545103N/A70 tok/s5890%
APIMart

apimart

APIMart is a pay-as-you-go, OpenAI-compatible AI API gateway operated by Hangzhou Huanzhi Network Technology Co., Ltd. It provides unified access to more than 500 third-party text, image, video, and audio models, with consolidated billing, multi-provider routing, and automatic failover.

  • More free-model options
25716$0.015/MN/A9980%

Announcements

success8/14/2026

Synced official pricing: gemini-3.6-flash

success8/13/2026

Model launched: deepseek-v4-pro-0813

success8/5/2026

Model launched: qwen3.8-max

success8/2/2026

Model launched: deepseek-v4-flash-0731

success7/25/2026

Model launched: claude-opus-5

success7/24/2026

Notice: cc max group multiplier 4 is live

success7/21/2026

Notice: special-price codex group multiplier 0.2 is live

success7/20/2026

Notice: gpt-drawing group multiplier 1.25 is live, supporting image generation 1, 2, 4k

success7/17/2026

Notice: Added stripe payment method

success7/16/2026

Model launched: kimi-k3

FAQ

What is the billing model for the relay station?

1. Offers multiple billing models: by request count, by token quantity, etc. 2. Real-time display of user's API usage and costs.

What should I do if an API request fails?

Common reasons for API request failures and solutions: 1. Authentication error: Check if the API key is correct 2. Insufficient balance: Please recharge your account in time 3. Parameter error: Refer to the documentation to check request parameters 4. Model unavailable: Try switching to another available model 5. Request timeout: May be due to network issues or high service load, please retry later If unresolved, contact online customer service.

How do I view my API call records and usage?

After logging in, you can view detailed API call records on the "Usage Log" page, including time, model, consumed token quantity, and cost information.

How do you ensure data security?

1. We do not store your request content and response data 2. All API requests use TLS encrypted transmission 3. Strict access control and permission management 4. Regular security audits and vulnerability scans.

What guarantees are there for service availability?

We promise 99.9% service availability, ensured through global distributed deployment and load balancing for stable service. For enterprise users, we provide Service Level Agreement (SLA) guarantees.

How do I get help if I encounter problems?

1. Consult the detailed development documentation 2. Contact online customer service support.

Is there example code available for development?

We provide example code and SDKs for multiple programming languages, including Python, Node.js, Java, etc., see the "Documentation" section at the top for details.

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 20-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.