add-model-price

À utiliser lors de l'édition de worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, des niveaux de prix, des identifiants de tokenizer ou des regex matchPattern…

npx skills add https://github.com/langfuse/langfuse --skill add-model-price

Add Model Price

Use this skill for model pricing changes in worker/ and shared LLM type updates in packages/shared/.

When to Apply

  • Editing worker/src/constants/default-model-prices.json
  • Editing packages/shared/src/server/llm/types.ts
  • Adding a new priced model
  • Updating provider prices, cache pricing, or tier conditions
  • Expanding regex coverage for Bedrock, Vertex, Azure, or provider-prefixed model names
  • Auditing default model prices for stale, missing, or unmatched provider pricing
  • Auditing official provider docs for newly released major models that should receive default pricing and, when appropriate, selectable-model coverage

How to Read This Skill

  • Use this SKILL.md as the high-level workflow and helper index.
  • Open only the specific reference file that matches the task.

Quick Start Checklist

Adding a New Model

  • Gather official pricing from the provider documentation.
  • Generate a lowercase UUID for the model entry.
  • Create a matchPattern that covers supported provider formats.
  • Add at least one default pricing tier.
  • Write every per-token price as <USD per MTok>e-6 (0.1e-6, not 1e-7).
  • Map every supported semantic usage bucket to the provider aliases Langfuse may persist.
  • Insert the pricing entry into worker/src/constants/default-model-prices.json.
  • Update packages/shared/src/server/llm/types.ts if the model should be selectable in playground or evaluation flows.
  • Validate the JSON after editing.

Updating an Existing Model

  • Update the relevant prices, keys, tiers, or regexes.
  • Refresh updatedAt to today's ISO-8601 timestamp.
  • Validate the JSON after editing.

Reference Map

TopicRead this whenFile
Schema and tier rulesYou need the entry shape or pricing-tier invariantsreferences/schema-and-tiers.md
Provider sources and price keysYou need official pricing URLs, per-token conversion, or provider-specific usage keysreferences/provider-sources-and-price-keys.md
Provider usage-key matrixYou are adding or changing OpenAI, Gemini, Anthropic, or Bedrock usage keysreferences/provider-usage-key-matrix.md
Match patternsYou are editing matchPattern regexes or provider coveragereferences/match-patterns.md
Workflow and validationYou are applying the end-to-end edit process or checking common mistakesreferences/workflow-and-validation.md
Automated audit modeYou are running a scheduled/default-price audit and need CI-safe edit rulesreferences/automated-audit.md
Audit memoryYou need optional per-model context retained from a useful prior automated auditreferences/model-audit-memory.md

Deterministic Helpers

  • Pricing file validator: node .agents/skills/add-model-price/scripts/validate-pricing-file.mjs
  • Match-pattern tester: node .agents/skills/add-model-price/scripts/test-match-pattern.mjs --model <modelName> --accept <sample...> --reject <sample...>
  • Direct regex tester: node .agents/skills/add-model-price/scripts/test-match-pattern.mjs --pattern '(?i)^(openai/)?(gpt-4o)$' --accept gpt-4o openai/gpt-4o --reject gpt-4o-mini

Plus de skills de langfuse

frontend-browser-review
langfuse
Utilisez cette compétence lorsqu’un changement affecte ce que les utilisateurs voient ou font dans le navigateur.
frontend-large-feature-architecture
langfuse
À utiliser lors de la construction, de la modification ou du refactoring de grandes fonctionnalités frontend Langfuse, de listes virtualisées, de grands tableaux, de composants contrôleurs, de fonctionnalités locales…
skill-developer
langfuse
Créer et gérer des compétences Claude Code conformément aux meilleures pratiques d’Anthropic. À utiliser lors de la création de nouvelles compétences, de la modification de skill-rules.json, de la compréhension des déclencheurs…
langfuse-prompt-migration
langfuse
Migrer les prompts codés en dur vers Langfuse pour le contrôle de version et l'itération sans déploiement. Utiliser lorsque l'utilisateur souhaite externaliser les prompts, déplacer les prompts vers Langfuse,…
incident-alert-tickets
langfuse
Read and, after human approval, update the Linear `incident-alert` knowledge base. Use before and after investigating a named Datadog monitor,…
refactor-react-effects
langfuse
Refactorisation des utilisations évitables de useEffect de React dans le code frontend de Langfuse. À utiliser lors de l'ajout, de la révision ou de la suppression d'effets ; de l'initialisation de formulaires ou d'état d'interface locale à partir de…
sentry-instrumentation
langfuse
Decide whether and how errors report to Sentry. Use when touching capture or error-handling paths in `web/**`, triaging Sentry noise, or changing Sentry…
posthog-instrumentation
langfuse
Product analytics with posthog. Use when adding a meaningful user action or feature in `web/**`, touching PostHog capture code, or answering product-usage…