🔬 R&D Model Strategy

Date: 2026-08-03 Status: Proposed (awaiting Pat’s approval)

Requirements

The R&D agent needs to:

  • Analyze websites — fetch URLs, read content, extract structure
  • Process YouTube — transcribe videos, summarize content
  • TTS / Audio — generate or analyze speech
  • Web scraping — pull data from pages programmatically
  • Image analysis — screenshots, diagrams, visual content
  • Write findings — to vault and sandbox experiments

Model Recommendation

Primary: openrouter/google/gemini-2.5-flash

Why:

  • Natively multimodal (text, vision, audio, video, URL)
  • Extremely cheap on OpenRouter (~$0.075/M input tokens)
  • 1M token context window (can handle entire websites)
  • Built-in URL fetching via OpenCode’s webfetch tool
  • Proven working in our sandbox tests

Limitations through OpenCode:

  • Can’t directly analyze images (OpenCode’s adapter strips vision)
  • YouTube needs external tooling (yt-dlp for transcripts)

For Vision/Image Analysis: openrouter/openai/gpt-5.4-mini

When Gemini can’t handle it through OpenCode:

  • GPT-5.4-mini can read images via file paths
  • Affordable multimodal option
  • Good for screenshot analysis, diagram reading

For Deep R&D: openrouter/qwen/qwen3-vl-30b-a3b-instruct

  • Open-source vision-language model
  • Can analyze images and code
  • Good for technical document analysis
  • Very cheap on OpenRouter

How R&D Tasks Actually Work

The R&D model won’t do everything in one shot. It orchestrates:

TaskToolModel
Fetch websitecurl / OpenCode webfetchGemini 2.5 Flash
YouTube transcriptyt-dlp → textGemini 2.5 Flash
Screenshot analysisplaywright → image → GPT-5.4-miniGPT-5.4-mini
Web scrapingpython + requests/bs4Gemini 2.5 Flash (code gen)
TTS generationHermes text_to_speech toolN/A (uses configured TTS)
Document analysisRead file → modelGemini 2.5 Flash or Qwen VL
Write findings to vaultJ.A.R.V.I.S. writesN/A

Updated Model Strategy Table

Use CaseModelProviderCost
Primary (Hermes daily)glm-5.2z.aiLowest
Paperclip agentsdeepseek-v4-flash-0731OpenRouter$0.003-0.01/task
R&D / multimodalgemini-2.5-flashOpenRouter~$0.075/M
R&D visiongpt-5.4-miniOpenRouterModerate
Heavy reasoning (CEO review)Claude Sonnet 5OpenRouterModerate
Heavy codingGPT-5.6 TerraOpenRouterModerate