Mars HK is an API relay service hosted in Hong Kong on port 31328, providing access to AI language models through OpenAI-compatible endpoints with low latency for Asia-Pacific users.
http://mars-hk.duckdns.orgVerify ownership to unlock provider management features:
https://mars-hk.duckdns.org:31328https://mars-hk.duckdns.org:13111Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
Mars HK appears to expose OpenAI-compatible API endpoints from a Hong Kong-hosted relay service. The public website currently returns a 404 page, so this entry is documented conservatively from the reachable domain, existing sibling metadata, and observed endpoint behavior.
Compare 13 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
| Model | Input ($/M) | Output ($/M) | Audit | Speed | Latency |
|---|---|---|---|---|---|
| - | - | — | 54.3 t/s | 6.62 s | |
codex-auto-review | - | - | — | 49.7 t/s | 2.15 s |
gpt-5.5 | - | - | — | 30.1 t/s | 6.53 s |
deepseek-v4-prodefault | $75.00/M | $75.00/M | — | — | — |
deepseek-v4-flashdefault | $75.00/M | $75.00/M | — | — | — |
glm-5.1default | $75.00/M | $75.00/M | — | — | — |
MiniMax-M2.7default | $75.00/M | $75.00/M | — | — | — |
minimaxai/minimax-m2.7default | $75.00/M | $75.00/M | — | — | — |
gpt-5.4-minidefault | $75.00/M | $450.00/M | — | 128.3 t/s | 4.45 s |
glm-5-turbodefault | $75.00/M | $75.00/M | — | — | — |
gpt-5.4default | $75.00/M | $450.00/M | — | 48.5 t/s | 6.08 s |
gpt-5.4(high)default | $75.00/M | $450.00/M | — | — | — |
gpt-5.4(xhigh)default | $75.00/M | $450.00/M | — | — | — |
Showing 13 of 13 model rows
| Time | Model | Speed | Latency |
|---|---|---|---|
| May 9, 01:30 AM | gpt-5.4-mini | 148.52 tok/s | 3.07s |
| May 9, 01:29 AM | gpt-5.4-mini | 135.95 tok/s | 6.05s |
| May 6, 04:34 AM | gpt-5.5 | 59.52 tok/s | 3.94s |
| Apr 28, 01:30 PM | MiniMax-M2.7-highspeed | 54.34 tok/s | 6.62s |
| Apr 26, 06:13 AM | gpt-5.5 | 29.21 tok/s | 16.15s |
| Apr 26, 06:03 AM | codex-auto-review | 49.68 tok/s | 2.15s |
| Apr 24, 02:33 PM | gpt-5.5 | 31.97 tok/s | 6.97s |
| Apr 24, 01:59 PM | gpt-5.5 | 17.28 tok/s | 6.21s |
| Apr 24, 01:59 PM | gpt-5.4-mini | 100.55 tok/s | 4.24s |
| Apr 24, 01:57 PM | gpt-5.4 | 53.62 tok/s | 8.01s |
Compare Mars HK alternatives against 6 nearby API providers using 180 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| Mars HK mars-hk-duckdns-org-31328 Mars HK is an API relay service hosted in Hong Kong on port 31328, providing access to AI language models through OpenAI-compatible endpoints with low latency for Asia-Pacific users. | Current provider baseline | 22 | 42 | N/A | 52 tok/s | 0.7% |
| CaMeL AI api-kr777-top CaMeL AI provides an OpenAI-compatible API gateway with extensive model coverage and pricing options. |
| 194 | 4 | $88.81/M | 93 tok/s | 99.1% |
api-vectorengine-ai Vector Engine provides an API platform aggregating access to over 500 AI large models with OpenAI API compatibility and global deployment. |
| 182 | 6 | $6.08/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. |
| 177 | 6 | $8.65/M | 90 tok/s | 99.7% |
api-futureppo-top Future Hub is a large-scale OpenAI-compatible API gateway at api.futureppo.top with extensive model coverage and pricing data. |
| 132 | 223 | N/A | 263 tok/s | 0.6% |
llm-api Provides API access to large language models for developers. |
| 82 | 71 | N/A | N/A | 73.6% |
180txt-cn 180txt API provides an OpenAI-compatible API relay for multiple AI models. |
| 37 | 77 | $18.03/M | 42 tok/s | 0.7% |
