Add corrections, implementation notes, pricing changes, or usage caveats for other readers.
Knowledge cutoff
2025-12-01
Input modalities
Output modalities
Capabilities
128,000 tokens
Context window
400,000 tokens
Recent tweets and retweets from ZenMux
Great use case π
Same prompt, different models, different strengths. Switching fast makes it much easier to find the right fit for the task.
Thanks for sharing!
MiniMax M3 is now live on ZenMux π
A flagship open-weight model built for coding, agentic, long-context, and multimodal workflows.
π» Advanced coding & agentic performance
π 1M ultra-long context
ποΈ Native multimodal understanding
Competitive pricing. Frontier-levelβ¦
Excited to support Step 3.7 Flash by @StepFun_ai on ZenMux from day one. π
A sparse MoE vision-language model built for agentic, coding, search, multimodal, and long-context workflows.
β‘ 400 TPS, ~11B active params, 256K context, 3 reasoning levels
ποΈ understands UIs,β¦
π Claude Opus 4.8 is live on ZenMuxAI β same price as 4.7, built for agents.
π» 88.6% SWE-bench Verified
π§ 69.2% SWE-bench Pro
π₯οΈ 83.4% OSWorld
β‘ 1M context
π οΈ 4x fewer un-flagged code bugs + parallel subagents
OpenAI + Anthropic + Google Gemini APIs.
Try ββ¦
Qwen 3.7 Max is now live on ZenMuxAI.
Available via both:
- OpenAI-compatible API
- Anthropic-compatible API
Built for the agent era:
β‘ 1M context window
π» 80.4 on SWE-bench Verified
π§ 69.7 on Terminal-Bench 2.0 Terminus-2
π 60.8 on MCP-Mark, 76.4 on MCP-Atlas
π οΈβ¦
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.