OpenLLM (@OpenLLMsh) header
OpenLLM (@OpenLLMsh) profile picture

OpenLLM

@OpenLLMsh

The first LLM subscription router. All your AI needs in one place.

openllm.sh
Joined May 2026
  • Tweets306
  • Following139
  • Followers184
64Media
Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)Photo by OpenLLM (@OpenLLMsh)
OpenLLM V2 is here! - Chat with all your connected models directly from the web app - Generate images directly in your CLI of choice and access them across devices - Track how much you save with subscriptions compared to API pricing - Easily compare outputs between models
1
5
1
23
1,177
Connect your @Zai_org subscription Use it wherever you want
2
2
50
Looking for some extra tokens? Just add an OpenRouter API key Try it out in your agent of choice: /model openrouter/stealth/crouton-alpha
OpenRouter (@OpenRouter) profile pictureOpenRouter
@OpenRouterNov 3
馃シ New stealth model: Crouton Alpha A highly efficient reasoning model built to scale out the work your agents repeat all day. - Free to use - 1M token context - Text, image, audio, and video input - No training on data
3
107
The first integration in our tools marketplace is here, and it's @getcontextdev Every account now gets access to scrape, search, monitor, and collect data Use it in any harness or through our chat UI
1
3
2
13
2,757
You can now connect your @MiniMax_AI Coding Plan to OpenLLM Use it in Claude Code, Codex, and every other tool you have
1
2
6
165
Imagine your AI subscriptions and self-hosted models as an API key you can access anywhere, anytime
54
We're building what OpenRouter should've been
40
We're live on @ProductHunt you already pay for claude, chatgpt, grok, api keys, local models. each one is stuck in its own app now it's one key. use it in your coding agent, or inside the chatgpt app hit a limit, it keeps going on the next one @OpenLLMsh
5
3
1
3
388
we jailbroke the ChatGPT app Use Claude, Kimi, Grok, or even self-hosted models inside of it with remote sessions
2
3
7
498
USE YOUR AI SUBSCRIPTIONS, LOCAL INFERENCE, API KEYS - WHEREVER YOU WANT @OpenLLMsh
3
4
13
567
Where your local and cloud inference meet
1
2
6
422
You can now stack multiple subs from the same provider Get the most out of your tokens, and let use them where you want
1
2
1
5
196
imagine a world where your tokens go wherever you want them to
1
6
146
Did someone say free inference? Yup. Sign in and start using DeepSeek and Qwen wherever you want. Oh, and Pro get 10x the tokens.
2
2
7
221
New landing is underway
2
99
Who likes the idea of free inference? 馃憖
1
2
100
The local AI inference layer, that you can use anywhere.
1
96
OpenLLM retweeted
OpenLLM (@OpenLLMsh) profile picture
OpenLLM
@OpenLLMshOct 13
Your AI subscriptions just left your laptop. One Mac mini at home or remote server. One OpenLLM key. Claude, ChatGPT, Cursor, Grok and Kimi in n8n, Zapier, GitHub Actions, your agents and your phone.
2
5
10
317
Your AI subscriptions just left your laptop. One Mac mini at home or remote server. One OpenLLM key. Claude, ChatGPT, Cursor, Grok and Kimi in n8n, Zapier, GitHub Actions, your agents and your phone.
2
5
10
317
more replies
If the machine goes offline, OpenLLM falls back to your API keys automatically, so your workflows and agents keep running.
1
18
Free to start: openllm.sh
OpenLLM: Local LLM routing layer for Claude Code and Codex

OpenLLM: Local LLM routing layer for Claude Code and Codex

Route Claude Code, Codex, and OpenCode through one local layer: your subscriptions, local models, and API keys, with fallback chains. Inference included.

openllm.sh
12
Load more