@commonstack_ai

One API to access the best AI models in the world. Faster agents, lower costs.

commonstack.ai/
Joined January 2026
  • Tweets109
  • Following23
  • Followers418
Which is your pick? Both live on commonstack.ai now.
5
10
1
18
705
Opus 5. Refreshed homepage. More to come.
8
6
6
25
2,939
A glimpse into a month of production traffic through Commonstack: -12.9M+ requests -168B+ tokens -70 models -20%+ savings off list prices On to the next.
9
10
8
36
4,433
GPT-5.6 family is live on Commonstack. Route your agents to Sol, Terra and Luna. openai/gpt-5.6-sol openai/gpt-5.6-terra openai/gpt-5.6-luna Same key as your Claude, Gemini, DeepSeek and Kimi calls.
4
13
2
32
4,378
How do you evaluate an LLM router fairly? Most benchmarks look at prompts, but routers operate at an agentic-step level. A router that saves money but breaks the task could be worse than no router. We open-sourced TwinRouterBench to measure this honestly. 🧵
6
15
3
44
2,489
Fraction of the bill. Same results. Fully local, open source, works with any client. Just > pipx install uncommon-route github.com/CommonstackAI/Unc…

Uncommonroute - automatic local router for api savings

38
42
76
134
450,723
Run Claude Code with Commonstack in 4 steps: - generate an API key - set 4 environment variables - run claude - /status to verify Set it up now in 5 minutes with @alex_mirran.
8
19
7
38
3,695
Opus 4.7 shipped yesterday. It's now live on Commonstack, alongside 47 other models from 11 providers. Your frontier can be a full portfolio.
2
6
24
1,106
Model selection is driven by Thompson Sampling on real benchmark data (PinchBench), not price assumptions. Three feedback clicks change routing immediately. It gets smarter as you use it. Works with Codex, Claude Code, Cursor, OpenClaw, any OpenAI SDK client. pip install, set your upstream, serve.
1
4
214
Most routing tools match keywords. UncommonRoute has zero keyword lists. It's an ML classifier trained on structural features and character n-grams. No hardcoded rules. Works across 16 languages without language-specific config. Difficulty is a continuous 0-1 score, not a coarse label. Harder tasks automatically get more quality weight.
1
5
87
Not every prompt needs your most expensive model. ~80% of your requests are low-complexity steps: tool selection, result parsing, status checks. UncommonRoute routes those to cheaper models automatically to lower your API costs by >90% Open source, runs locally, MIT licensed.
6
11
4
33
1,989
If you're an OpenClaw🦞 builder and you've been hesitating about which model to pick, this quick comparison might help:
5
4
2
19
1,280
⚡ Attention OpenClaw builders 🦞 — GLM-5-Turbo works great with OpenClaw and can significantly accelerate agent workflows. @Zai_org It pairs naturally with OpenClaw and helps accelerate agent reasoning loops and tool usage. Try it on Commonstack.ai commonstack.ai/model-library…
1
2
18
302
Gemini 3 Flash ranked #1 on PinchBench on OpenClaw agent tasks success rate, followed by MiniMax M2.1 and Kimi K2.5. Don't forget Gemini 3 Flash Lite: same family, built for high-volume workloads at even lower prices. All on commonstack.ai
Peter Steinberger 🦞
@steipeteMar 7
Interesting benchmark on which model is best for @openclaw pinchbench.com

Best Models by Success Rate | PinchBench

Find the best AI model for your OpenClaw agent. Compare success rates, speed, and cost across 100+ LLMs on real coding tasks.

pinchbench.com
3
5
1
17
1,117
🦞Clawbox Updates🦞 > We’ve been seeing an explosion of new Skills across the OpenClaw ecosystem lately. You can now create and manage your own custom Skills directly in Clawbox > On the safety side, we also added support for customizable Soul.md with starter templates, so you can shape how your agent behaves from the start without needing to build everything from scratch.
5
1
1
17
717
Gemini 3.1 Pro is here @commonstack_ai Model highlights: > ARC-AGI-2 reasoning score jumps to 77.1% (~2× previous gen) > Wins 13/16 major benchmarks > API pricing unchanged Learn more about Commonstack.ai
Google Gemini
@GeminiAppFeb 19
Gemini 3.1 Pro is here: A smarter model for your most complex tasks. Building on the Gemini 3 series, 3.1 Pro is a step forward in reasoning. It's designed for tasks where a simple answer isn’t enough, taking advanced reasoning and making it useful for your hardest challenges.🧵

3
3
17
574
Qwen 3.5 is rolling out @Alibaba_Qwen Core capabilities: > Reasoning feels sharper across real tasks > Multilingual workflows (CN ↔ EN especially) feel native now > Long-context stability keeps improving → better for agents & research stacks > Structured outputs are cleaner, making integrations far less painful > Coding performance is catching up to models that cost way more Try Qwen 3.5 on Commonstack.ai
Qwen
@Alibaba_QwenFeb 16
🚀 Qwen3.5-397B-A17B is here: The first open-weight model in the Qwen3.5 series. 🖼️Native multimodal. Trained for real-world agents. ✨Powered by hybrid linear attention + sparse MoE and large-scale RL environment scaling. ⚡8.6x–19.0x decoding throughput vs Qwen3-Max 🌍201 languages & dialects 📜Apache2.0 licensed 🔗Dive in: GitHub: github.com/QwenLM/Qwen3.5 Chat: chat.qwen.ai API：modelstudio.console.alibabac… Qwen Code: github.com/QwenLM/qwen-code Hugging Face: huggingface.co/collections/Q… ModelScope: modelscope.cn/collections/Qw… blog: qwen.ai/blog?id=qwen3.5
2
3
9
671
Replying to @gradientintern
@gradientintern
188
Load more