An OpenAI-compatible API relay providing access to multiple AI models, hosted at api.minewuer.top.
https://xn--ykqa11zbv4abvki1bu63blp2a.comhttps://api.minewuer.topRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
Compare 13 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
| Model | Input ($/M) | Output ($/M) | Audit | Speed | Latency | Tests |
|---|---|---|---|---|---|---|
| — | — | — | 62.0 t/s | 9.27 s | 5 | |
| — | — | — | 48.5 t/s | 1.00 s | 5 | |
gemini-3.1-pro-preview-high-search | — | — | — | 114.9 t/s | 14.75 s | 5 |
| Free | Free | — | — | — | — | |
deepseek-ai/deepseek-v4-prodefault | Free | Free | — | — | — | — |
deepseek-v4-flashdefault | Free | Free | — | — | — | — |
deepseek-v4-pro-chatdefault | Free | Free | — | — | — | — |
| $0.0001 | $0.0001 | — | — | — | — | |
google/gemma-4-31b-itdefault | Free | Free | — | — | — | — |
官网反代/qwen3.5-plusdefault | $75.00 | $75.00 | — | — | — | — |
官网反代/qwen3.5-plus-fastdefault | $75.00 | $75.00 | — | — | — | — |
官网反代/qwen3.6-plusdefault | $75.00 | $75.00 | — | — | — | — |
官网反代/qwen3.6-plus-fastdefault | $75.00 | $75.00 | — | — | — | — |
Showing 13 of 13 model rows
| Time | Model | Speed | Latency |
|---|---|---|---|
| Apr 22, 11:01 AM | grok-4.20-0309 | 61.96 tok/s | 9.27s |
| Mar 19, 05:44 AM | grok-4.20-beta | 48.46 tok/s | 1.00s |
| Feb 20, 10:07 AM | gemini-3.1-pro-preview-high-search | 114.85 tok/s | 14.75s |
Token limits have been enabled. Maintenance on channels and such is scheduled for the next two days, so it's likely that the service will be unavailable during this period.
Future restrictions will be placed on agents like openclaw and Hermes. Users should switch providers, as public resources are limited and will be depleted.
ollama has weekly limits. I'm not in the mood to manage the site these days, so you understand. Wait for May Day to update channels and add weekly quotas.
Not many models available. Please do not abuse. Later, daily limits will be set (input plus output 2kw). I will open a window for submitting requests to increase limits; reasonable requests will be approved.
Someone registered three accounts for intense testing, making 30 times the usual requests in half a day (36,600 times). If you see this, come to the group to explain. Later, I will implement limits on registration and requests.
Grok's official site is down, so the channel is temporarily removed.
Changed the domain. Both .com and .top are still accessible and requests work, meow.
DeepSeek's official reverse proxy has been restored.
Grok is back to normal.
The channels from Baishan Zhisuan for GLM5, DeepSeek, and MiniMax are now free. Go play with those.
Gemini is affected by 429 rate limiting and is temporarily unavailable. Please use the free GPT for now (thanks to user Xingjianya, meow).
Access to Gemini's Pro model has been enabled. You can try it out, but it's quite unstable at night.
Currently, only Gemini 3 Flash is guaranteed to be available. GPT will be made free later.
All GPT team accounts have been banned, so it's likely unavailable from today. I don't feel like replenishing them. If you want to use GPT, let me know, and I'll replenish then.
Grok can generate images normally now. Big Banana will be handled later, so tired.
Gemini is restored. You can continue playing.
ChatGPT is back on the site. If you don't have Gemini, you can use that. Codex is specialized for code; don't use it if you're not coding. (I'm not sure how much you can play; I've set up four team account proxies, so just play for now.)
All CLI accounts have been rate-limited. Gemini might take a few days to recover. In a couple of days, I'll get some team accounts for you to play GPT. If Gemini can't be restored, I'll refund everyone. Anyway, I won't run away. Very sorry QwQ.
Compare MineWuer API alternatives against 6 nearby API providers using 365 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| MineWuer API api-minewuer-top An OpenAI-compatible API relay providing access to multiple AI models, hosted at api.minewuer.top. | Current provider baseline | 68 | 69 | $15.21/M | 75 tok/s | 48.5% |
| 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. |
| 168 | 182 | $0.022/M | 102 tok/s | 100% |
llm-whitedream-top RenRen API runs a New API-powered gateway on llm.whitedream.top for aggregated access to multiple AI models. |
| 250 | 0 | $12.24/M | 271 tok/s | 99.7% |
ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 200 | 0 | $0.098/M | 171 tok/s | 93.7% |
api-xinjianya-top Xinjianya API is an OpenAI-compatible API relay at api.xinjianya.top. Service availability may be limited. |
| 184 | 209 | $0.119/M | 67 tok/s | 100% |
api-6345ywz-cn 6345ywz API is an OpenAI-compatible API relay providing access to multiple AI models with competitive pricing. |
| 98 | 0 | $1.82/M | 248 tok/s | 99.8% |
tianxu-api Tianxu API provides an AI model relay service with multiple access points and stable connectivity. |
| 344 | 1 | $23.50/M | 93 tok/s | 100% |
