Wanmei Xiaomu operates a unified AI gateway for developers and teams who want OpenAI-compatible access to a broad catalog of language models. Its public status endpoint indicates centralized quota management, CNY-based pricing, daily check-in support, and a web console for managing keys and usage.
ai.api.xn--fiqs8s
Wanmei Xiaomu is a Chinese AI model gateway that provides OpenAI-compatible access to hundreds of models with centralized quota and account management.
- Models
- 44 models
- From
- --
- Speed
- 106 tok/s
- Updated
- 6/25/2026
- Latency
- 0.00 s
- Created At
- 8/13/2025
- Recharge Rate
- ¥1.00 per $1 quota
Features
API Endpoints
- Endpoint 1Historical / Unverified
https://ai.api.xn--fiqs8s - Endpoint 2Historical / Unverified
http://ai.api.xn--fiqs8s
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 丸美小沐
Health Check
API Benchmarks & Pricing
Compare 38 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
claude-sonnet-4-8default | $8.28/M | $41.40/M | - | - |
claude-sonnet-4-7default | $8.28/M | $41.40/M | - | - |
claude-opus-4-8default | $13.50/M | $67.50/M | - | - |
claude-opus-4-7default | $13.50/M | $67.50/M | - | - |
gpt-5.5default | $1.60/M | $12.80/M | - | - |
deepseek-v4-prodefault | $4.00/M | $6.00/M | - | - |
deepseek-v4-flashdefault | $75.00/M | $75.00/M | - | - |
gemini-3.1-flash-previewdefault | $1.20/M | $4.20/M | - | - |
gemini-3-pro-previewdefault | $4.00/M | $22.80/M | - | - |
gpt-5.4default | $1.60/M | $12.80/M | - | - |
gemini-3.1-pro-previewdefault | $4.00/M | $23.20/M | - | - |
claude-sonnet-4-6default | $8.28/M | $41.40/M | - | - |
claude-opus-4-6default | $13.50/M | $67.50/M | - | - |
gemini-3-flash-previewdefault | $1.62/M | $4.05/M | - | - |
gpt-5.2default | $2.40/M | $19.20/M | - | - |
BLOOMZ-7B | - | - | 70.6 t/s | 2.46 s |
| - | - | 39.4 t/s | 4.75 s | |
deepseek-reasonerdefault | $0.990/M | $0.990/M | 29.9 t/s | 4.71 s |
deepseek-v3default | $75.00/M | $75.00/M | 26.7 t/s | 3.41 s |
| - | - | 158.3 t/s | 0.91 s | |
| - | - | 155.1 t/s | 1.62 s | |
| - | - | 275.1 t/s | 1.28 s | |
| - | - | 125.2 t/s | 1.07 s | |
| - | - | 125.0 t/s | 1.40 s | |
| - | - | 188.4 t/s | 1.06 s |
Showing 25 of 38 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Feb 20, 07:45 AM | Phi-4 | 41.62 tok/s | 0.90s |
| Feb 14, 04:31 PM | qwen-72b | 102.22 tok/s | 3.11s |
| Feb 14, 04:10 PM | gemini-2.0-flash-lite-preview-02-05 | 175.81 tok/s | 0.87s |
| Feb 14, 04:08 PM | qwen2.5-72b-instruct | 96.05 tok/s | 2.68s |
| Feb 14, 04:07 PM | qwen2.5-72b-instruct | 89.24 tok/s | 2.47s |
| Feb 14, 04:04 PM | o3-mini | 19.75 tok/s | 6.67s |
| Feb 14, 03:58 PM | qwen2.5-7b-instruct | 34.15 tok/s | 1.01s |
| Feb 14, 03:57 PM | gpt-4o-mini | 78.22 tok/s | 1.05s |
| Feb 14, 03:56 PM | gemini-1.5-flash | 158.26 tok/s | 0.91s |
| Feb 14, 03:56 PM | gemini-1.5-flash-8b | 302.85 tok/s | 1.17s |
Similar API Provider Alternatives to Compare
Compare 丸美小沐 alternatives against 6 nearby API providers using 230 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 丸美小沐 ai-api-xn-fiqs8s Wanmei Xiaomu is a Chinese AI model gateway that provides OpenAI-compatible access to hundreds of models with centralized quota and account management. | Current provider baseline | 44 | 22 | N/A | 106 tok/s | 9950% |
| FreeModel freemodel FreeModel is an OpenAI-compatible API gateway that provides access to frontier AI models through a unified endpoint, with free usage options for developers. |
| 17 | 0 | N/A | 253 tok/s | 9980% |
| Deno Deploy Proxy deno-deploy-proxy An AI API proxy deployed on Deno Deploy, providing OpenAI-compatible model access. |
| 1 | 0 | N/A | 180 tok/s | 9960% |
| 阿里云百炼 DashScope dashscope Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models. |
| 299 | 0 | N/A | 79 tok/s | 8670% |
| Gitee AI gitee-ai Gitee AI provides a platform for AI model hosting, inference, and deployment with access to open-source LLMs. |
| 260 | 0 | N/A | 88 tok/s | 7240% |
| 火山引擎 Ark volcengine-ark Volcengine Ark is ByteDance's enterprise AI platform, offering Doubao series models and third-party LLMs via OpenAI-compatible API. |
| 163 | 0 | N/A | 41 tok/s | 9940% |
| SiliconFlow siliconflow Provides cost-effective generative AI cloud services based on open-source models for text, image, video, and audio generation. |
| 154 | 0 | N/A | 59 tok/s | 6020% |
Announcements
🎉 System Upgrade Announcement — The quota system has been optimized. The exchange rate has been unified to 1:1. Model prices remain unchanged. Account quotas have been automatically synchronized. Please contact the administrator if you have any questions.
v1.0.0 System Upgrade
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.

