霸气公益平台 at ai.121628.xyz is a LinuxDO community LLM relay by user jun9. Supports rate (gpt-5.4 sometimes routed to 5.1). Models: DeepSeek, embedding-001, Gemini, K2, Kimi, Minimax, Qwen, text-embedding-004. Supports LDC, immersive translate. No NSFW. 2026-01-19 temporary outage; 2026-01-20 restored.
A
Baqi Gongyi (ai.121628.xyz) is a LinuxDO LLM relay by user jun9. Broad model coverage. Supports immersive translate and LDC.
- Models
- 104 models
- From
- --
- Speed
- --
- Updated
- 7/8/2026
- Latency
- --
- Created At
- 4/20/2026
- Recharge Rate
- ¥1.00 per $1 quota
Features
DrawingTaskData Export
Login Methods
GitHubLinuxDO
API Endpoints
- Endpoint 1Historical / Unverified
https://ai.121628.xyz
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 霸气公益平台
Health Check
99%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 95 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
gemma-26b-a4b-it-free |
gemma-4-31b-it-free |
glm-4-9b-free |
glm-z1-9b-free |
gpt-oss-20b |
inkling-free |
ising-calibration-31b |
laguna-s-2.1-free |
ling-3.0-flash-free |
llama-3.1-70b-free |
llama-3.1-8b-free |
llama-3.1-nemoguard-8b-content |
llama-3.1-nemoguard-8b-topic |
llama-3.2-11b-vision-free |
llama-3.2-1b-embed |
llama-3.2-1b-free |
llama-3.2-3b-free |
llama-3.2-90b-vision-free |
llama-3.3-70b-free |
llama-3.3-nemotron-super-49b |
longcat-2.0-free |
mistral-medium-3.5-128b |
mistral-nemotron |
nemoretriever-parse |
nemotron-3-embed-1b |
Showing 25 of 95 model rows
Recent Test Records
No test records available
Similar API Provider Alternatives to Compare
Compare 霸气公益平台 alternatives against 6 nearby API providers using 321 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 霸气公益平台 ai-121628-xyz Baqi Gongyi (ai.121628.xyz) is a LinuxDO LLM relay by user jun9. Broad model coverage. Supports immersive translate and LDC. | Current provider baseline | 104 | 67 | N/A | N/A | 2270% |
| 初叶🍂Furry API ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 1,067 | 164 | $8.50/M | 171 tok/s | 3120% |
| 星见雅 API api-xinjianya-top Xinjianya API is an OpenAI-compatible API relay at api.xinjianya.top. Service availability may be limited. |
| 498 | 211 | N/A | 67 tok/s | 9480% |
| MapleLeaf API ai-071129-xyz MapleLeaf API runs a New API-powered gateway on ai.071129.xyz for aggregated access to multiple AI models. |
| 470 | 292 | N/A | 38 tok/s | 9950% |
| 42公益站 api-42w-shop 42 Gongyi Station is a LinuxDO community-run LLM API relay built by user 4242 for testing welfare-station performance. Supports Gemini, DeepSeek, GPT models, with Gemini rate-limit 10/min. Compatible with immersive-translate and LDC. |
| 278 | 373 | N/A | N/A | 9860% |
| 猫羽霖API huashang-dpdns-org An OpenAI-compatible API relay providing access to multiple AI models with extensive model coverage and pricing data. |
| 1,378 | 21 | $0.0042/M | 57 tok/s | 9110% |
| 小水管 API edge-pieixan-icu Pie-Xian (小水管) provides an OpenAI-compatible API relay with multiple endpoints including api.pie-xian.com and edge nodes. |
| 514 | 0 | $547.50/M | 260 tok/s | 9920% |
Announcements
default7/30/2026
System Maintenance Notice - 2026-07-30
Due to data transmission issues between primary and replica databases, additional synchronization and backup processing is required.
Maintenance will begin on July 30, 2026 at 17:00 (system will operate normally during maintenance), estimated duration: 10 minutes.
Maintenance will not affect any user actions or operations; it will enhance stability and data security.
default7/26/2026
Platform Model Testing Rule Update Notice
To ensure stable platform services and reasonable allocation of interface resources, the platform's model testing rules are updated as follows:
Effective immediately, all free models and models with zero billing are completely prohibited from testing operations. The system will automatically detect violations and impose random bans on accounts that use zero-billing or free models for testing.
For regular testing needs or interface availability checks, please use the platform's regular paid billing models.
default7/13/2026
📢 Important Notice - 2026-07-13
The following new models are now officially available: GPT Series | GPT 5.5, GPT 5.6 OPUS Series | OPUS-4.8, OPUS-4.7
Currently Free models are provided for use, and the following adjustments have been made:
📋 Adjustment Details
- Clear original account balance — All account balances will be reset to zero
- Free models available — You can now use Free models for free
💡 Current Usage Suggestions
- ✅ Use now: Choose Free models to experience the service or use LDC to recharge
default7/12/2026
Interface Endpoint Usage Optimization Notice
Currently, some upstream interfaces of the platform have native format errors, and the NewAPI automatic conversion endpoint has adaptation issues that may cause request errors and abnormal responses.
To ensure a good user experience and request stability, we strongly recommend using the /chat/completions endpoint for requests. You can also test locally and select model endpoints with proper compatibility.
default7/11/2026
Model Fallback Mechanism Adjustment Notice
Due to the recent high call volume and number of online users for the free series models (glm-5.2-free, kimi-2.6-free, etc.), high load may cause system errors and abnormal calls.
To ensure service stability and avoid sudden failures, the platform has now integrated the mimo-2.5-pro model as a fallback. Going forward, when free models exceed load limits or become temporarily unavailable, the system will automatically switch to the fallback model to handle requests, ensuring normal service availability.
default7/8/2026
Notice of System Failure and Recovery - 2026-07-08
Dear User,
Hello!
Due to a sudden database anomaly, the system was unavailable from 2026-07-08 08:00 to 2026-07-08 17:00.
After urgent investigation and repair, the system services are now fully restored. We sincerely apologize for the inconvenience caused and thank you for your patience and understanding!
If you encounter any further issues, please feel free to provide feedback.
default7/7/2026
Announcement - 2026-07-07
Dear User,
The original glm-free group has been officially taken offline and replaced with xxxxx-free (e.g., kimi-k2.6-free).
The system will automatically update to the latest NewAPI version every 2 days at 04:30, which will cause brief unavailability. Please be aware!
Free channels are aggregated channels such as MoTa, ShangTang, NVIDIA, etc., all free of charge, but stability is not guaranteed!
Normal channels are official, Jiguang, opencode, etc., currently operating as public welfare, and may consider integrating LDC for payment in the future!
ongoing5/27/2026
🎉 Announcement | Xiaomi 2.5 Series Models Now Free for a Limited Time! Dear Users, To thank everyone for your continued support and love for AI Public Welfare Models, we are pleased to announce:
The Xiaomi 2.5 Series Models limited-time free trial is now open!
⏰ Event Details Free trial duration: 3 days from today Model scope: All Xiaomi 2.5 series models Future arrangements: Adjustments may be made flexibly after the trial ends, please keep an eye on announcements
If there are any changes, we will notify you immediately. Thank you for your understanding and support!
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.