One Gateway, Infinite Models
Joined March 2025
- Tweets 333
- Following 43
- Followers 690
- Likes 106
238 Photos and videos
Don't let an upstream outage become your outage.
AIHubMix now supports Model Mapping and Automatic Fallback at the API-key level.
Configure it once in the dashboard:
• No client-side changes
• No custom gateway or proxy
• No request-level routing logic
✅ Map model aliases to real upstream models
✅ Automatically switch to a backup model when the primary fails
✅ Pay only for the model that actually responds
Docs:
docs.aihubmix.com/en/api/Mod…
1
224
Compared with OpenRouter or LiteLLM, the biggest difference is operational simplicity.
You don't need to: • Pass model arrays in every request • Maintain your own proxy layer • Give up native Claude or Gemini protocol support
Everything is configured once at the API-key level.
There's also a cost optimization benefit:
Use free models as your primary option and paid models as fallback. Under normal conditions you'll consume free quotas, and when rate limits or outages occur, traffic seamlessly switches to the backup model.
173
Step 3.7 Flash by @StepFun_ai is now available on AIHubMix with a limited-time 90% discount ⚡
Input Tokens only: $0.02 /M tokens
Output Tokens only: $0.13 /M tokens
A cost-efficient choice for high-volume API calls, agents, and production workflows.
Try it here:
aihubmix.com/model/step-3.7-…
#AIHubMix #StepFun #LLM #AIModels
1
1
178
New on AIHubMix: Claude Fable 5 🚀
Anthropic's newest frontier model is live — see what's new 👇
Full changelog → docs.aihubmix.com/en/update/…
1
209
What Anthropic says about Fable 5 👇x.com/claudeai/status/206439…
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
144
Opus 4.8 just dropped on AIHubMix — and it's the most honest Claude yet.
Same price as 4.7, gains across agentic coding, reasoning & computer use, ~4x less likely to let code flaws pass unremarked.
Here's what changed 👇 aihubmix.com/model/claude-op…
1
1
391
🚀 Qwen3.7-Plus-Preview by @Alibaba_Qwen — live on AIHubMix！
💻Stronger coding — cleaner code generation, debugging & repo-level edits
🧠 Sharper reasoning & agentic tool-use for complex, multi-step tasks
📚 Long-context for large codebases & docs
🆓 Free for a limited time — don't miss it! 👉 aihubmix.com/model/qwen3.7-p…
2
350
The new Qwen3.7-Max from @Alibaba_Qwen is live on AIHubmix；The price of this model on AIHubmix is only $1.69 for input and $5.07 for output per million tokens, with the model supplied by Alibaba Cloud.aihubmix.com/model/qwen3.7-m…
1
1
1
489
AIHubmix has added the API for this model at the first opportunity, come and give it a try!
May 21
📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era.
A versatile foundation for agents that actually get things done:
🧑💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it.
🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration.
⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000 tool calls, zero hand-holding.
🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere.
API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio.
Go build something wild!🏃🏃♂️
📖 Blog: qwen.ai/blog?id=qwen3.7
✅ Qwen Studio: chat.qwen.ai/?models=qwen3.7…
⚡️ API：modelstudio.console.alibabac…
5
684
AIHubmix has launched support for gemini-3.5-flash at the first opportunity.
aihubmix.com/model/gemini-3.…
1
324
Xiaomi's MiMo series is live on AIHubMix — multiple models free to try.
Flash, Pro, Omni — accessible through one key.
Browse the catalog → aihubmix.com/model?utm_sourc…
1
3
506
🚀 Baidu's latest flagship ERNIE 5.1 from
@ErnieforDevs is now LIVE on AIHubmix!
Beats DeepSeek-V4-Pro on Agent benchmarks
Creative writing near Gemini 3.1 Pro
99.6 on AIME26 (with tools)
#4 globally on Arena Search (#1 Chinese model)
Try ERNIE 5.1 instantly 👉aihubmix.com/model/ernie-5.1…
#ERNIE51 #BaiduAI #AIHubmix #LLM
1
593
🔥 Gemini 3.1 Flash-Lite is NOW LIVE on AIHubMix!
Google DeepMind's Hardcore Masterpiece — The Ultimate King of Price-to-Performance:
True Multimodal Powerhouse: Text, image, video, audio & PDF input → text output
1 Million Token Context
Input $0.25 / M tokens • Output $1.50 / M tokens
Try it first→ aihubmix.com/model/gemini-3.…
#Gemini #GeminiFlashLite #GoogleDeepMind #AIHubMix #MultimodalAI #LongContext #Cheap #FastAI #AIPricing #NewMode
1
497
AIHubmix retweeted
gemini 3.1 flash-lite is here
it's our most cost-efficient model, optimized for high-volume agentic tasks, translation, and simple data processing
222
421
4,232
591,679
GPT-Image-2 is now free on AIHubMix！
Experience👉 aihubmix.com/model/gpt-image…
AIHubMix user special: Unlock 10 free experiences of this premium AI model.
From product shots and posters to avatars, illustrations, e-commerce assets, social visuals, and TikTok livestream screenshots — create polished, designer-level images in one click.
#GPTImage2 #aiimage #freetoken #OpenAI #AIHubMix
1
1
356
POV: When your robot suddenly feels...
The impossible emotion, the heartbreaking realism — all created with GPT Image 2 on AIHubMix.
Try it now: aihubmix.com/model/gpt-image…
352
GPT-5.5 is now free on AIHubMix!
OpenAI's latest flagship — available at zero cost.
👉 aihubmix.com/model/gpt-5.5-f…
The current #1 model on SWE-Bench
Verified — 88.7%, ahead of Claude Opus 4.7 (87.6%)
Terminal-Bench 2.0: 82.7% SOTA
Unlock 10 complimentary experiences today!
#GPT55 #OpenAI #AIHubMix #AgenticAI #AICoding #LLM
1
2
317