HUBAPI
One API layer for teams building with multiple LLM providers
What it does
Access leading LLM providers through one planned gateway, one key, one balance, and one dashboard. Join the private beta to test smart routing, scoped keys, model comparison, and usage visibility. Plan for cost savings with provider comparison, intelligent routing, caching, and fallback strategies. HUBAPI is designed to let developers keep their existing LLM SDK workflow while routing requests through a unified gateway during the private beta.
Does the same job
all alternatives →
- ALAny-LLM – Lightweight router to access any LLM Provider2025 · github.com · ▲125
We built any-llm because we needed a lightweight router for LLM providers with minimal overhead. Switching between models is just a string change : update "openai/gpt-4" to "anthropic/claude-3" and you're done. It uses official provider SDKs when available, which helps since providers handle their own compatibility updates. No proxy or gateway service needed either, so getting started is pretty straightforward - just pip install and import. Currently supports 20+ providers including OpenAI, Anthropic, Google, Mistral, and AWS Bedrock. Would love to hear what you think!
- ALA lightweight AI gateway to 100+ models, in TS2024 · github.com · ▲37
We are Rohit & Ayush, we created Portkey this year March to help tackle some challenges we had seen while building apps based on GPT3, 3.5, 4, and the DevOps principles we brought to the scene to help tackle them. We believe, a solid, performant, and reliable gateway lays the foundation to help build the next level of LLM apps. It decreases excessive reliance on any one company and takes the focus back to building instead of spending time fixing the nitty gritties of different providers and making them work together. Features: Blazing fast (9.9x faster) with a tiny footprint (~45kb…
- FAForeman, a self-hosted LLM gateway for cost aware model routingJul 2026 · github.com · ▲15
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com