CM-API-公益站 at api.chengmo.cc.cd is a LinuxDO welfare relay by user chengmo. Per-call pricing 0.01 USD. Models: Grok, Kimi, Qwen. Registration 50 USD. Supports LDC, immersive translate. Does not allow NSFW.
CM-API (api.chengmo.cc.cd) is a LinuxDO LLM API relay by user chengmo. 0.01 USD per call. Grok, Kimi, Qwen. Supports immersive translate and LDC.
- Models
- 198 models
- From
- $0.010/M
- Speed
- 122 tok/s
- Updated
- 7/8/2026
- Latency
- 0.00 s
- Created At
- 4/20/2026
- Recharge Rate
- ¥1.00 per $1 quota
Features
Login Methods
API Endpoints
- Three-Network Optimization
https://api.chengmo.cc.cd
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 CM-API 公益站
Health Check
API Benchmarks & Pricing
Compare 89 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
BAAI/bge-large-en-v1.5 | - | - |
BAAI/bge-large-zh-v1.5 | - | - |
BAAI/bge-reranker-v2-m3 | - | - |
FunAudioLLM/SenseVoiceSmall | - | - |
inclusionai/ling-3.0-flash:free | - | - |
Kwai-Kolors/Kolors | - | - |
openai-fast | - | - |
PaddlePaddle/PaddleOCR-VL-1.5 | - | - |
poolside/laguna-s-2.1:free | - | - |
Qwen/Qwen2.5-7B-Instruct | - | - |
Qwen/Qwen3-8B | - | - |
Qwen/Qwen3.5-4B | - | - |
tencent/Hunyuan-MT-7B | - | - |
THUDM/GLM-4-9B-0414 | - | - |
THUDM/GLM-Z1-9B-0414 | - | - |
google/diffusiongemma-26b-a4b-it国产模型 | $75.00/M | $75.00/M |
meta/llama-3.2-90b-vision-instruct国产模型 | $75.00/M | $75.00/M |
mistral-smallchat | $0.0005/request | - |
nvidia/ising-calibration-1.5-31b国产模型 | $75.00/M | $75.00/M |
nvidia/llama-3.1-nemoguard-8b-content-safety国产模型 | $75.00/M | $75.00/M |
nvidia/llama-3.1-nemotron-nano-8b-v1国产模型 | $75.00/M | $75.00/M |
nvidia/llama-3.1-nemotron-nano-vl-8b-v1国产模型 | $75.00/M | $75.00/M |
nvidia/llama-3.1-nemotron-safety-guard-8b-v3国产模型 | $75.00/M | $75.00/M |
nvidia/nemotron-mini-4b-instruct国产模型 | $75.00/M | $75.00/M |
nvidia/nvidia-nemotron-nano-9b-v2国产模型 | $75.00/M | $75.00/M |
Showing 25 of 89 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jul 26, 12:01 PM | DeepSeek-R1-0528-Qwen3-8B | 122.28 tok/s | 2.43s |
Similar API Provider Alternatives to Compare
Compare CM-API 公益站 alternatives against 6 nearby API providers using 715 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| CM-API 公益站 api-chengmo-cc-cd CM-API (api.chengmo.cc.cd) is a LinuxDO LLM API relay by user chengmo. 0.01 USD per call. Grok, Kimi, Qwen. Supports immersive translate and LDC. | Current provider baseline | 198 | 0 | $0.010/M | 122 tok/s | 9950% |
| 小天公益站 new-api-xt-url-com A unified gateway API for large language models, offering access to multiple providers with competitive pricing and stability. |
| 137 | 2 | $0.0022/M | 150 tok/s | 9960% |
| 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 | 9530% |
| 初叶🍂Furry API ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 1,021 | 152 | $18.00/M | 171 tok/s | 2830% |
| 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. |
| 495 | 2 | $0.054/M | 260 tok/s | 9910% |
| 6345ywz API api-6345ywz-cn 6345ywz API is an OpenAI-compatible API relay providing access to multiple AI models with competitive pricing. |
| 466 | 0 | $0.0000686/M | 272 tok/s | 9750% |
| Cuz AI ai-cuz-lab-space Cuz AI runs an OpenAI-compatible relay at ai.cuz-lab.space with broad model coverage, public pricing, and stable throughput for chat and coding workloads. |
| 393 | 0 | $0.020/M | 170 tok/s | 9980% |
Announcements
Updated the "Service Statement and Terms of Use"
——————Debugging phase, please do not recharge or purchase anything——————
Preparing to switch to premium lines; insufficient resources to maintain too many models. Billing will change to pay-as-you-go.
Temporarily pausing usage. I'll use existing stock to adjust scripts....
The number pool is about to run out. I'm out for business and temporarily not fixing it.
If prompted with insufficient token balance, delete the token and recreate it. Wait for me to maintain slowly.
Maintenance — Migrating database.
As long as registration doesn't error, if you can't log in, try logging in twice. Contact below for feedback!
Genius programmer is about to decline~~~~~~~~~~~~~~
Haphazardly added a bunch of messy models. In a couple of days, I'll see what's usable and filter them.
3.26 -- Evening maintenance, mainly addressing website loading delay issues.
Please do not use GPT for immersive translation or continuously test without calling.
Recommended to use:
gpt-5.3 code
gpt-5.4
Prohibited to use GPT for translation or continuous testing.
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.

