New Models on Hugging Face
-
LLM-OS-Models published multiple Gemma 4 Terminal SFT fine-tunes, including E4B and E2B variants (1-epoch and 2-epoch each). These are text-generation transformers optimized for terminal-use scenarios, based on Google’s Gemma 4 architecture. The most popular variant, LLM-OS-Models/gemma-4-E4B-it-Terminal-SFT-Native-Liquid-2Epoch, has 2,333 downloads.
-
Kenpache released perspective-aware-financial-sentiment, an XLM-RoBERTa-based model for multilingual financial sentiment analysis.
New Models on OpenRouter
-
Claude Opus 4.7 (Fast) by Anthropic — 1M token context window, priced at $30/M tokens (prompt). A faster variant of Anthropic’s most capable model.
-
Perceptron Mk1 by Perceptron — 32K context window, priced at $0.15/M tokens (prompt). A new entrant in the OpenRouter catalog.
Trending GitHub Repos
-
huangserva/3DCellForge ⭐1,825 — AI-powered interactive 3D model generation, inspection, and presentation studio built with JavaScript.
-
alchaincyf/huashu-md-html ⭐517 — A bidirectional md/html pipeline: anything → md → beautiful HTML → md, powered by MarkItDown, Pandoc, and html-to-markdown.
-
simonlin1212/a-stock-data ⭐499 — A full-stack data toolkit for China A-Share stock market with 6-layer architecture, 15 endpoints, and 7 data sources.
-
yaassin12/DeepSeek-V4-Pro-App ⭐359 — Desktop app for DeepSeek V4 Pro featuring 1.6T MoE architecture and 1M token context window.
-
sunyouzhi2003/LSFG-Desktop ⭐355 — Lossless Scaling 2026 universal frame generation (LSFG 3) supporting X2, X3, X4 multipliers.
Limited Free Models — Expiry Watch
Several xAI models expire today on OpenRouter’s limited free tier:
| Model | Context | Prompt Price | Expiry |
|---|---|---|---|
| Grok 4.1 Fast | 2M tokens | $0.20/M tokens | May 15 |
| Grok 4 Fast | 2M tokens | $0.20/M tokens | May 15 |
| Grok Code Fast 1 | 256K tokens | $0.20/M tokens | May 15 |
| Grok 4 | 256K tokens | $3/M tokens | May 15 |
| Grok 3 Mini | 131K tokens | $0.30/M tokens | May 15 |
| Grok 3 | 131K tokens | $3/M tokens | May 15 |
Still available for a few more weeks:
- Mistral 7B Instruct v0.1 — expires May 30 — $0.11/M tokens prompt / $0.19/M tokens completion
- Gemini 2.0 Flash Lite — expires June 1 — $0.075/M tokens prompt / $0.30/M tokens completion — 1M token context