> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/phases/phase_40/session_09_model_intelligence_and_pricing.md). # Session 09: Model Intelligence And Pricing **Session ID**: `phase40-session09-model-intelligence-and-pricing` **Status**: Not Started **Estimated Tasks**: \~12-25 **Estimated Duration**: 2-4 hours *** ## Objective Implement the smallest durable model-intelligence subset and live-only pricing overlay needed for Ministry analytics. *** ## Scope ### In Scope (MVP) * Create a Hermes-scoped Ministry model subset instead of adding a repo-level `src/data/model-intel.json` file. * Use upstream `model-intel.json` only as source material for fields Ministry renders. * Implement keyless OpenRouter pricing only in local live mode, with bundled static snapshot fallback and visible provenance. * Disable live pricing in public/demo mode so demo remains fixture-only. * Ensure default Ministry lineup data covers Claude Opus 4.8, GPT-5.5, GLM 5.2, and DeepSeek V4 Pro without missing metric gaps. * Add model row parsing, static fallback, optional live-price failure, and stable sorting tests. ### Out of Scope * Repo-wide model intelligence data. * Claiming live benchmark data. * Fetching live pricing in public/demo mode. *** ## Prerequisites * [ ] Session 08 catalog and context decisions are available. *** ## Deliverables 1. Hermes-scoped Ministry model rows and pricing fallback behavior. 2. Live-local versus bundled-snapshot pricing provenance path. 3. Tests for default lineup availability, ranking inputs, live-price failure, demo-disabled live pricing, and missing-metric fallbacks. *** ## Success Criteria * [ ] Ministry analytics can rank by benchmark, cost, and speed. * [ ] Analytics do not claim live benchmark data. * [ ] Pricing says live OpenRouter only for values returned by the live overlay. * [ ] Required default lineup models render without `unknown` gaps for required metrics. *** ## Folded Source Session Split The section below preserves the original Phase 40 session split detail for this session, including dependencies, decisions, outputs, and acceptance checks. ### Session 09: Model Intelligence And Pricing **Objective**: Implement the smallest durable model-intelligence subset and live-only pricing overlay needed for Ministry analytics. **Scope**: * Create a Hermes-scoped Ministry model subset instead of adding a repo-level `src/data/model-intel.json` file. * Use upstream `model-intel.json` only as source material for fields Ministry actually renders. * Implement live keyless OpenRouter pricing only in live local mode, with bundled/static snapshot fallback and visible provenance. * Disable live pricing in public/demo mode so demo remains fixture-only. * Ensure default Ministry lineup data covers Claude Opus 4.8, GPT-5.5, GLM 5.2, and DeepSeek V4 Pro without missing metric gaps. * Add model row parsing, static fallback, optional live-price failure, and stable sorting tests. **Outputs**: * Hermes-scoped Ministry model rows and pricing fallback behavior. * A live-local versus bundled-snapshot pricing provenance path. * Tests for default lineup availability, ranking inputs, live-price failure, demo-disabled live pricing, and missing-metric fallbacks. **Dependencies / Notes**: * Depends on Session 08. * Decision: the local app may fetch `https://openrouter.ai/api/v1/models` without a key for live pricing, because it is user-visible public model data. The UI must fall back to bundled snapshot prices, use a 30 minute stale time, and label whether a shown price is live OpenRouter data or bundled snapshot data. **Acceptance Checks**: * Ministry analytics can rank by benchmark, cost, and speed. * Analytics do not claim live benchmark data. Pricing says "live OpenRouter" only for values returned by the live overlay and "bundled snapshot" otherwise. * Required default lineup models render without `unknown` gaps for required metrics. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/phases/phase_40/session_09_model_intelligence_and_pricing.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.