ZenMux

AI, Simplified & Assured.
The enterprise-grade LLM gateway with a unified API, full observability, and automatic compensation.

[ZenMux @ZenMuxAI]

Hey everyone! 👋 If you're into the latest models and love chatting about AI, join our Discord Server! 🙋‍♀️🙋🙋‍♂️Chat directly with our dev team, talk about the freshest models, and show off what you build with ZenMux. 🚀Click the link https://t.co/TTBImWlJOw be part of the community.

[ZenMux @ZenMuxAI]

Great use case 👀

Same prompt, different models, different strengths. Switching fast makes it much easier to find the right fit for the task.

Thanks for sharing!

[GameFi Labs @GameFiLabs]

昨天我分享了用 @ZenMuxAI 接入 Claude Opus 4.8（Bedrock）帮我优化币安永续合约自动交易系统的事。

实际跑下来感觉挺靠谱的，尤其是风控和单腿失败处理那块，确实帮我把几个容易踩的坑提前看到了。谢谢大家这段时间的留言和鼓励！

有朋友还特意私信给我分享了一个多模型对比的帖子，我马上就去试了试。今天干脆在 @ZenMuxAI 里用同一个 prompt，把 Claude 4.8 和 Gemini 3.5 Flash 拉一起又 PK 了一轮（还是高频套利指南的深度评审任务）。

结果挺有意思的：
Claude 像个老司机，特别会泼冷水，风险点看得又准又狠
Gemini 更像技术架构师，方案给得特别细，还直接甩代码例子
两个模型风格完全不一样，结合起来用感觉比单用一个强多了。

说实话，用 @ZenMuxAI 最大的方便就是切换模型太快了，不用每次折腾 Key 和配置，直接就能对比。正在把两个模型的建议融合到我的系统里，后面有实际效果再来更新。

正在做币安永续自动化交易的朋友欢迎交流，一起讨论讨论风控、延迟这些实际问题

PS:体验链接已放在评论区，感兴趣的可以自行去体验一下！

[ZenMux @ZenMuxAI]

MiniMax M3 is now live on ZenMux 🚀

A flagship open-weight model built for coding, agentic, long-context, and multimodal workflows.

💻 Advanced coding & agentic performance
📚 1M ultra-long context
👁️ Native multimodal understanding

Competitive pricing. Frontier-level performance.

🔥 Limited-time 50% off:
https://t.co/bnOFeJnJ1c

[ZenMux @ZenMuxAI]

Excited to support Step 3.7 Flash by @StepFun_ai on ZenMux from day one. 🚀

A sparse MoE vision-language model built for agentic, coding, search, multimodal, and long-context workflows.

⚡ 400 TPS, ~11B active params, 256K context, 3 reasoning levels
👁️ understands UIs, charts, docs, and images — then writes code or calls tools to act on what it sees
🔎 built for deeper web + visual search, with more sources and follow-up
🛠️ reliable tool use: less drift, fewer broken tool calls, 98%+ on τ²-bench across difficulty levels
🧠 works with Claude Code, KiloCode, Hermes Agent, OpenClaw, and MCP-style workflows
🖥️ runs locally on Mac Studio M4 Max, DGX Spark, and AMD AI Max+ 395

Try it on ZenMux now → https://t.co/bAbNArM5SY
One API for capable models.

#StepFun #ZenMux #AIAgents #LLM

[ZenMux @ZenMuxAI]

🚀 Claude Opus 4.8 is live on ZenMuxAI — same price as 4.7, built for agents.

💻 88.6% SWE-bench Verified
🧠 69.2% SWE-bench Pro
🖥️ 83.4% OSWorld
⚡ 1M context
���️ 4x fewer un-flagged code bugs + parallel subagents
OpenAI + Anthropic + Google Gemini APIs.
Try → https://t.co/9bD5q2hVRg

[ZenMux @ZenMuxAI]

Qwen 3.7 Max is now live on ZenMuxAI.
Available via both:
- OpenAI-compatible API
- Anthropic-compatible API
Built for the agent era:
⚡ 1M context window
💻 80.4 on SWE-bench Verified
🧠 69.7 on Terminal-Bench 2.0 Terminus-2
🔌 60.8 on MCP-Mark, 76.4 on MCP-Atlas
🛠️ 35 hours of autonomous work, 1,158 tool callsOne subtle but important upgrade:
Qwen 3.7 Max is much better at staying productive across long, multi-step workflows — planning, coding, calling tools, debugging, and improving instead of stopping early.
That matters a lot for:
Coding, Agents, research, office automation, and long-context workflows.
Now available on ZenMuxAI.
Try it now → https://t.co/GmF7hpfUCb

@ZenMuxAI #Qwen #AI #LLM #VibeCoding #OpenSource #ZenMuxAI

[ZenMux @ZenMuxAI]

Gemini 3.5 Flash just dropped at Google I/O 2026 — and it's already live on ZenMux API, FREE to try 🚀

⚡ Flagship-level intelligence at Flash speed
🤖 #1 on MCP Atlas (83.6%), Toolathlon (56.5%), Finance Agent (57.9%)
🌐 Tops MMMU-Pro & CharXiv Reasoning benchmarks
💻 Beats Gemini 3.1 Pro on coding & agentic tasks
Drop-in OpenAI-compatible. No setup headaches.
Try free → https://t.co/uGoRPmFZhE
#Gemini #GoogleIO #AI #LLM #ZenMux

[thinkthinking @thinkthinking_]

@ZenMuxAI now supports the @OpenAI Image protocol.
You can call OpenAI image models natively through the OpenAI SDK:

Base URL:
https://t.co/0EgfB4kdXa

Supported models:
- openai/gpt-image-2
- openai/gpt-image-1.5

Docs:
https://t.co/bxYoZFKwtw

For agent workflows, install the ZenMux image generation skill:

npx skills add ZenMux/skills

[ZenMux @ZenMuxAI]

GPT‑5.5 Instant is now live on ZenMuxAI.

Available via both:
- OpenAI-compatible API
- Anthropic-compatible API

This is a surprisingly meaningful upgrade over GPT‑5.3 Instant:
- 52.5% fewer hallucinated claims
- much better self-correction
- shorter + denser responses
- stronger personalization & memory usage
- major gains in math / science / multimodal evals

One subtle but important change:
GPT‑5.5 Instant is much better at realizing its own reasoning mistakes and continuing to debug instead of stopping early.

That matters a lot for:
Coding, Agents, research, long-context workflows.

Now available on ZenMuxAI.

[OpenAI @OpenAI]

GPT-5.5 Instant is starting to roll out in ChatGPT.

It’s a big upgrade, giving you smarter, clearer, and more personalized answers in a warmer, more natural tone.

And it's also more concise, which we heard you wanted. We think you'll love chatting with it.

[ZenMux @ZenMuxAI]

@deepseek_ai 🔗DeepSeek: DeepSeek V4 Pro (Free)：https://t.co/DZxaHV8see
🔗DeepSeek: DeepSeek V4 Flash (Free)：https://t.co/5lg9FE3ZmB

[ZenMux @ZenMuxAI]

DeepSeek-V4 @deepseek_ai is HERE FREE on @ZenMuxAI ! 🚀
API & Chat are free for a limited time – jump right in!

Two editions, one mission:
🔷 V4-Pro – max performance, built for agentic coding. Real‑world feel: better than Sonnet 4.5, close to Opus 4.6 (non‑thinking).
⚡ V4-Flash – smaller, faster, lower cost. Simple agent tasks? On par with Pro.

🔥 One API, all protocols – OpenAI Chat/Responses + Anthropic Messages. Use it inside Codex, Claude Code, OpenCode, etc.
PAYGO & Builder Plan already supported.

Try for free now → @ZenMuxAI

#DeepSeek #DeepSeekV4 #AI #LLM #VibeCoding #OpenSource #ZenMuxAI

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.

🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.

Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!

📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM

1/n

[ZenMux @ZenMuxAI]

📢 Ling-2.6-1T from @TheInclusionAI is live on @ZenMuxAI 🔥

Ant Group's trillion-param MoE flagship. 50B active per token. Open-source SOTA on SWE-bench Verified, AIME & agent benchmarks — no thinking tokens needed ⚡️

🔗 https://t.co/NO5Qjbny7R

[ZenMux @ZenMuxAI]

📢Two new Qwen 3.6 models just dropped on @ZenMuxAI

Qwen3.6-Flash — Speed-first reasoning with MoE architecture. Low latency, high throughput, built for agentic workflows.

Qwen3.6-Max-Preview — Alibaba's flagship model. Tops 6 coding benchmarks including SWE-Bench Pro & SkillsBench. 260K context with Thinking Preservation.

Try them now👇
🔗 https://t.co/bMIHvobQOY
🔗 https://t.co/1ysXnqdYef

[ZenMux @ZenMuxAI]

Hey @everyone 👋 — OpenAI GPT‑5.5 & GPT-5.5 pro Now Live on ZenMux!

📊 Selected Benchmarks

🏁 Terminal-Bench 2.0: 82.7%
🌐 BrowseComp: 84.4%
🧪 OSWorld-Verified: 78.7%
🧮 FrontierMath Tier 1–3: 51.7%
🔐 CyberGym: 81.8%

🔗 https://t.co/RRmW876HiJ 🔗https://t.co/xxwrxA86Xt

[ZenMux @ZenMuxAI]

🚀 Tencent Hunyuan Hy3 Preview is now live on ZenMux!

295B/21B MoE • 256K context • Fast & slow thinking hybrid

🤖 Top Agent scores on SWE-Bench Verified & BrowseComp
🔢 Highest reasoning score among CN models on Tsinghua Math PhD Exam
⚡ 40% inference efficiency boost over last gen
Try it now → https://t.co/nzOsHYZUUo

[ZenMux @ZenMuxAI]

🚀 Xiaomi MiMo-V2.5 series is now live on ZenMux!

Two models, one major upgrade:

MiMo-V2.5-Pro — rivals Claude Opus 4.6 & GPT-5.4 on agent tasks. Built a full compiler in 4.3hrs, scored 233/233. 42% fewer tokens than Kimi K2.6 💸

MiMo-V2.5 — native omnimodal agent (vision + audio + video), 1M context, 50% cheaper API vs prior gen ⚡

Try them now 👇
🔗 https://t.co/2XvCVszN4S
🔗 https://t.co/fw5pAdVaDx

[ZenMux @ZenMuxAI]

GPT-Image-2 is now live on ZenMux 🎉 (Free plan included)

OpenAI’s latest image generation model, GPT-Image-2, is now available on ZenMux. You can try it directly in ZenMux Studio Chat or use it via API — starting from the Free tier. PAYG billing is also supported.

✨ Highlights
• Strong prompt following with detailed UI, icons, and small text rendering (up to 2K via API)
• Multilingual text rendering: Chinese, Japanese, Korean, Hindi, Bengali 🌏
• Multiple visual styles: photorealistic, film look, comics, pixel art, cinematic frames 🎬
• Flexible aspect ratios from 3:1 to 1:3 📐
• Knowledge updated to Dec 2025 for more reliable visual content 📚
• Generate up to 8 consistent images in one go 🔁
🎯 Use cases
Ads, educational infographics, comic panels, game art, UI prototypes, social media graphics.
🚀 Try it on ZenMux
https://t.co/04tH4lsvPd

#AI #Agents #ZenMux #OpenAI #GPTImage2

[ZenMux @ZenMuxAI]

🚀 Kimi K2.6 is LIVE on ZenMux!

Moonshot's SOTA model.

🧠 13h+ continuous coding
🤖 300-agent swarm
⚡ 5-day autonomous runs
🔌 OpenAI/Anthropic compatible
Try it 👇
https://t.co/wYCMsr0mQd
#AI #Agents #ZenMux #Kimi