aidog-price-source-update

Update AiDog model pricing and max token metadata in models.json.

7|1|Updated Jun 12, 2026
One-click install
npx skills add https://github.com/lazygophers/aidog --skill aidog-price-source-update
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aidog-price-source-update
Source: https://github.com/lazygophers/aidog/tree/main/.claude/skills/aidog-price-source-update
Command: npx skills add https://github.com/lazygophers/aidog --skill aidog-price-source-update

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps maintain accurate model pricing and max token metadata for AiDog when provider prices change, new platforms are added, or context-based tier pricing needs to be updated.

Core Features & Use Cases

  • Pricing source maintenance: Update the canonical pricing data in models.json for model input, output, cache read, max_tokens, and context_window values.
  • Tiered pricing support: Define and adjust context_tiers so long-context requests resolve to the correct price tier without changing the core resolution logic.
  • Price sync and fallback behavior: Coordinate app-side periodic syncing through price_sync.rs and preserve resolve_price fallback chains so estimates remain stable during sync failures.
  • Use Case: When a provider revises model pricing or launches a new model, use this Skill to update the source data, validate fallback behavior, and keep cost estimates aligned.

Quick Start

Update the AiDog pricing source for the affected model, confirm any context tier changes, and verify that resolve_price still falls back correctly after sync.

Frequently Asked Questions about aidog-price-source-update

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

FAQPage Schema
How do I update AI model pricing in models.json when a provider changes costs?

Tiered context pricing works by defining and adjusting context_tiers so long-context requests resolve to the correct price tier automatically. This tier adjustment updates your pricing logic without changing the core resolution behavior.

Why does resolve_price fallback behavior fail during a price sync troubleshooting task?

The resolve_price fallback behavior may fail during price sync troubleshooting if app-side periodic syncing through price_sync.rs is interrupted. You must preserve the resolve_price fallback chains in your updates so estimates remain stable during sync failures.

What's the best way to onboard new model pricing metadata for an AI gateway?

The best way to onboard new model pricing metadata is to update the models.json canonical source with the correct max token metadata and tiered context pricing. You then validate the resolve_price fallback behavior to keep cost estimates aligned.

Does models.json need to be the canonical source for cost estimation updates?

Yes, models.json must be the canonical source for cost estimation updates. Preserving models.json as the canonical source ensures that price_sync-based runtime updates and resolve_price fallback behavior function correctly across all local gateway flows.

How do I run a monthly price refresh for AI model metadata without breaking sync?

To run a monthly price refresh without breaking sync, update the models.json source data and coordinate app-side periodic syncing through price_sync.rs. You must verify that resolve_price still falls back correctly after the sync completes.