openai-model-catalog-reuse

Consolidate OpenAI model metadata into context and pricing lookup tables.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/liuyu520/cc_source --skill openai-model-catalog-reuse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-model-catalog-reuse
Source: https://github.com/liuyu520/cc_source/tree/main/.claude/skills/openai-model-catalog-reuse
Command: npx skills add https://github.com/liuyu520/cc_source --skill openai-model-catalog-reuse

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Consolidates OpenAI model metadata to align context window mappings and pricing across model variants.

Core Features & Use Cases

  • Two unified lookup tables: OPENAI_MODEL_CONTEXT for context window size and OPENAI_MODEL_COSTS for pricing, ensuring consistent behavior across models.
  • Prefix-based context window mapping supports date-suffixed variants without duplicating entries.
  • Capability detection via probeCapabilities to surface model capabilities such as thinking support and 1M context threshold.
  • Use Case: Add a new model or update pricing by updating the two tables, then validate lookups.

Quick Start

Add a new model by updating both the context and pricing tables and run the validation commands to confirm lookups.

Frequently Asked Questions about openai-model-catalog-reuse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I centralize OpenAI model pricing and context window mappings?

Centralize OpenAI model pricing and context window mappings using two unified lookup tables: OPENAI_MODEL_CONTEXT for context size and OPENAI_MODEL_COSTS for pricing, ensuring consistent behavior across variants.

How do I add a new OpenAI model with date-suffixed variants to the catalog?

Add a new model by updating both the context and pricing tables, leveraging prefix-based context window mapping to support date-suffixed variants automatically, then run validation commands to confirm lookups.

How does capability detection work for OpenAI model features like thinking support?

Capability detection uses the probeCapabilities function to surface model features like thinking support and the 1M context threshold by probing the consolidated model metadata.

Can I use this model catalog approach for non-Anthropic families like Gemini?

Yes, you can extend support to non-Anthropic families like Gemini by applying the same context mapping and pricing table updates to synchronize their model metadata.

What is the best way to keep OpenAI model pricing tiers synchronized across variants?

The best way to keep pricing tiers synchronized is maintaining the OPENAI_MODEL_COSTS lookup table, which aligns pricing data across model variants and prevents duplication through prefix-based mapping.