# Hermes + North Mini Code: New FREE API! Page: https://stenobird.com/podcast/ai-news-today-julian-goldie-podcast-7573784/hermes-north-mini-code-new-free-api Text version: https://stenobird.com/podcast/ai-news-today-julian-goldie-podcast-7573784/hermes-north-mini-code-new-free-api.md Podcast: [AI News Today | Julian Goldie Podcast](https://stenobird.com/podcast/ai-news-today-julian-goldie-podcast-7573784) Published: 2026-06-21T02:10:01+00:00 Episode link: https://podcasters.spotify.com/pod/show/julian-goldie9/episodes/Hermes--North-Mini-Code-New-FREE-API-e3l2do7 Audio file: https://anchor.fm/s/10b0edd94/podcast/play/121763015/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-20%2F426521736-44100-2-7c915908e0985.mp3 Processing state: not_requested JSON: https://stenobird.com/v1/public/podcasts/ai-news-today-julian-goldie-podcast-7573784/episodes/hermes-north-mini-code-new-free-api Duration seconds: 589 ## Resource North Mini: The New Free AI Model for Agentic Coding Discover how to use North Mini, Cohere's new free agentic coding model, with the Hermes agent to build and run tools for zero cost. Learn how to set it up via the Open Router API or locally with Ollama to save your premium tokens for high-level tasks. 00:00 - Intro to North Mini 00:55 - How to Access North Mini 01:18 - Setting up Hermes Agent 01:39 - Running Locally with Ollama 02:45 - Model Benchmarks & Performance 04:07 - Creating AI Agent Profiles 05:21 - Token Management Strategy 07:31 - Building with Free Agents ## Actions - request_transcript: `POST https://stenobird.com/v1/public/podcasts/ai-news-today-julian-goldie-podcast-7573784/episodes/hermes-north-mini-code-new-free-api/transcription-requests` — Idempotently request low-priority transcript generation for this episode. - read_markdown: `GET https://stenobird.com/podcast/ai-news-today-julian-goldie-podcast-7573784/hermes-north-mini-code-new-free-api.md` — Read the agent-friendly Markdown representation of this episode resource. A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed. ## Transcript Full transcripts are not published on public pages unless there is a clear rights basis.