🧘 ZenMux

700 free requests/day — best Gemini coverage with 127 models

🧘

ZenMux

Speed: ⚡ 37 tok/s avg
Models: 127
Price: 700 req/day free
Status: ✅ Online
Avg Speed
37 tok/s
Models
127
Price
700/d free
Best For
Gemini, Qwen

💰 Plan & Pricing

✅
700 Free Requests/Day
Generous free tier with 700 requests per day. Good Gemini and Qwen coverage. No credit card needed.

🔑 API Key

sk-ss-...f72f

🌐 Endpoint

https://zenmux.ai/api/v1/chat/completions

📦 Key Models (127 total)

ModelSpeedCategoryNotes
google/gemini-2.5-flash⚡ 90 tok/sChat🥇 Best Gemini Flash
google/gemini-2.5-pro⚡ 41 tok/sChat/Reasoning🥇 Best Gemini Pro
llama-3.3-70b-versatile⚡ 52 tok/sChat2nd best for Llama
qwen/qwen3-32b⚡ 38 tok/sChatGood Qwen coverage
llama-4-maverick⚡ 42 tok/sChatLlama 4 Maverick
deepseek-r1⚡ 35 tok/sReasoningDeepSeek R1
claude-sonnet-4⚡ 30 tok/sChatClaude Sonnet 4
qwen3-235b⚡ 36 tok/sChat/CodingQwen3 235B
minimax-m2.7⚡ 27 tok/sChatMiniMax M2.7
zenmux/auto⚡ variesAuto⚡ Auto-selects best model

+ 117 more models with strong Gemini and Qwen coverage — auto routing available

💻 cURL Example

curl -X POST https://zenmux.ai/api/v1/chat/completions \
  -H "Authorization: Bearer sk-ss-...f72f" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

🐍 Python Example

from openai import OpenAI

client = OpenAI(
    api_key="sk-ss-...f72f",
    base_url="https://zenmux.ai/api/v1"
)

response = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

⚠️ Pitfalls & Notes

💡
Best Gemini Coverage — ZenMux offers the best Gemini 2.5 Flash at 90 tok/s. Good for Gemini-heavy workloads.
⚠️
Rate Limit — Free tier limited to 700 requests per day. Suitable for moderate but not heavy usage.

🏷️ Categories

Chat Vision Coding Reasoning Video