AI tools for models

Run open AI models on your own computer, free. Seeks private ChatGPT-style chat with open models, offline.

One Nous sign-in for 200+ models, hosted tools and agent hosting. Seeks hermes Agent users who want one bill instead of a key per lab.

One API key for 500+ models at provider list prices. Seeks trying and switching between many models without separate accounts.

Google's flagship reasoning model, top of LMArena right now. Seeks hard reasoning, coding and long agent runs through the Gemini API.

Anthropic's daily-driver flagship, #1 on Artificial Analysis. Seeks agentic coding, careful writing and long multi-step work.

OpenAI's mid-priced flagship with a 1M-token window. Seeks strong all-rounder for coding and agents at a lower price than GPT-6 Astra.

xAI's most capable Grok model for code and chat. Seeks cheap output tokens for a frontier model, with web and X search tools.

Open-weights MIT model with a rock-bottom official API price. Seeks cheap, fast everyday chat and coding; 1M context with vision.

Alibaba's 27B Apache-2.0 model that fits on one big GPU. Seeks running a capable model on your own machine, including images and video.

Moonshot's 2.8T open model, top open model on LMArena. Seeks best-in-class open weights for chat and coding.

Z.ai's open flagship, #2 open model on Artificial Analysis. Seeks strong open-weights reasoning and agents; a smaller MIT Flash sibling exists.

Xiaomi's MIT-licensed model, #1 open weights on Artificial Analysis. Seeks top open-weights intelligence at a very low listed price.

Nous Research's open fine-tunes, from 14B up to 405B. Seeks steerable, lightly filtered local chat and role-play on your own hardware.

A closed, hosted "decision model" that returns typed answers, not text. Seeks classification, scoring and routing inside your code, with calibrated confidence.