鱼皮AI导航
鱼皮AI导航
  • 主页
  • 社区
  • AI工具
  • AI知识库
  • AI提示词
  • MCP
  • Skills
  • AI学习资源
  • AI资讯
  • GitHub开源
登录/注册

model-registry-maintainer

维护模型注册表的完整性和时效性,同步更新各提供商的模型信息、功能特性、发布时间、价格及上下文窗口等核心参数,确保系统配置生成、成本估算与文档输出基于最新数据,并通过自动化脚本与外部数据库联动实现高效管理。

区块链商业与营销软件开发
访问 GitHub
文档Skills.MD
name
model-registry-maintainer
description
Guide for maintaining the MassGen model and backend registry. This skill should be used when adding new models, updating model information (release dates, pricing, context windows), or ensuring the registry stays current with provider releases. Covers both the capabilities registry and the pricing/token manager.

Model Registry Maintainer

This skill provides guidance for maintaining MassGen's model registry across two key files:

  1. massgen/backend/capabilities.py - Models, capabilities, release dates
  2. massgen/token_manager/token_manager.py - Pricing, context windows

When to Use This Skill

  • New model released by a provider
  • Model pricing changes
  • Context window limits updated
  • Model capabilities changed
  • New provider/backend added

Two Files to Maintain

File 1: capabilities.py (Models & Features)

What it contains:

  • List of available models per provider
  • Model capabilities (web search, code execution, vision, etc.)
  • Release dates
  • Default models

Used by:

  • Config builder (--quickstart, --generate-config)
  • Documentation generation
  • Backend validation

Always update this file for new models.

File 2: token_manager.py (Pricing & Limits)

What it contains:

  • Hardcoded pricing/context windows for models NOT in LiteLLM database
  • On-demand loading from LiteLLM database (500+ models)

Used by:

  • Cost estimation
  • Token counting
  • Context management

Pricing resolution order:

  1. LiteLLM database (fetched on-demand, cached 1 hour)
  2. Hardcoded PROVIDER_PRICING (fallback only)
  3. Pattern matching heuristics

Only update PROVIDER_PRICING if:

  • Model is NOT in LiteLLM database
  • LiteLLM pricing is incorrect/outdated
  • Model is custom/internal to your organization

Information to Gather for New Models

1. Release Date

  • Format: "YYYY-MM"
  • Sources:
    • OpenAI: https://openai.com/index
    • Anthropic: https://www.anthropic.com/news
    • Google DeepMind: https://blog.google/technology/google-deepmind/
    • xAI: https://x.ai/news

2. Context Window

  • Input context size (tokens)
  • Max output tokens
  • Look for: "context window", "max tokens", "input/output limits"

3. Pricing

  • Input cost per 1K tokens (USD)
  • Output cost per 1K tokens (USD)
  • Cached input cost (if applicable)
  • Sources:
    • OpenAI: https://openai.com/api/pricing/
    • Anthropic: https://www.anthropic.com/pricing
    • Google: https://ai.google.dev/pricing
    • xAI: https://x.ai/api/pricing

4. Capabilities

  • Web search, code execution, vision, reasoning, etc.
  • Check official API documentation

5. Model Name

  • Exact API identifier (case-sensitive)
  • Check provider's model documentation

Adding a New Model - Complete Workflow

Step 1: Add to capabilities.py

Add model to the models list and model_release_dates:

▼
python
复制代码
# massgen/backend/capabilities.py "openai": BackendCapabilities( # ... existing fields ... models=[ "new-model-name", # Add here (newest first) "gpt-5.1", # ... existing models ... ], model_release_dates={ "new-model-name": "2025-12", # Add here "gpt-5.1": "2025-11", # ... existing dates ... }, )

Step 2: Check if pricing is in LiteLLM (Usually Skip)

First, check if the model is already in LiteLLM database:

▼
python
复制代码
import requests url = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json" pricing_db = requests.get(url).json() if "new-model-name" in pricing_db: print("✅ Model found in LiteLLM - no need to update token_manager.py") print(f"Pricing: ${pricing_db['new-model-name']['input_cost_per_token']*1000}/1K input") else: print("❌ Model NOT in LiteLLM - need to add to PROVIDER_PRICING")

Only if NOT in LiteLLM, add to PROVIDER_PRICING:

▼
python
复制代码
# massgen/token_manager/token_manager.py PROVIDER_PRICING: Dict[str, Dict[str, ModelPricing]] = { "OpenAI": { # Format: ModelPricing(input_per_1k, output_per_1k, context_window, max_output) "new-model-name": ModelPricing(0.00125, 0.01, 300000, 150000), # ... existing models ... }, }

Provider name mapping:

  • "OpenAI" (not "openai")
  • "Anthropic" (not "claude")
  • "Google" (not "gemini")
  • "xAI" (not "grok")

Step 3: Update Capabilities (if new features)

If the model introduces new capabilities:

▼
python
复制代码
supported_capabilities={ "web_search", "code_execution", "new_capability", # Add here }

Step 4: Update Default Model (if appropriate)

Only change if the new model should be the recommended default:

▼
python
复制代码
default_model="new-model-name"

Step 5: Validate and Test

▼
bash
复制代码
# Run capabilities tests uv run pytest massgen/tests/test_backend_capabilities.py -v # Test config generation with new model massgen --generate-config ./test.yaml --config-backend openai --config-model new-model-name # Verify the config was created successfully cat ./test.yaml

Step 6: Regenerate Documentation

▼
bash
复制代码
uv run python docs/scripts/generate_backend_tables.py cd docs && make html

Current Model Data

OpenAI Models (as of Nov 2025)

In capabilities.py:

▼
python
复制代码
models=[ "gpt-5.1", # 2025-11 "gpt-5-codex", # 2025-09 "gpt-5", # 2025-08 "gpt-5-mini", # 2025-08 "gpt-5-nano", # 2025-08 "gpt-4.1", # 2025-04 "gpt-4.1-mini", # 2025-04 "gpt-4.1-nano", # 2025-04 "gpt-4o", # 2024-05 "gpt-4o-mini", # 2024-07 "o4-mini", # 2025-04 ]

In token_manager.py (add missing models):

▼
python
复制代码
"OpenAI": { "gpt-5": ModelPricing(0.00125, 0.01, 400000, 128000), "gpt-5-mini": ModelPricing(0.00025, 0.002, 400000, 128000), "gpt-5-nano": ModelPricing(0.00005, 0.0004, 400000, 128000), "gpt-4o": ModelPricing(0.0025, 0.01, 128000, 16384), "gpt-4o-mini": ModelPricing(0.00015, 0.0006, 128000, 16384), # Missing: gpt-5.1, gpt-5-codex, gpt-4.1 family, o4-mini }

Claude Models (as of Nov 2025)

In capabilities.py:

▼
python
复制代码
models=[ "claude-haiku-4-5-20251001", # 2025-10 "claude-sonnet-4-5-20250929", # 2025-09 "claude-opus-4-1-20250805", # 2025-08 "claude-sonnet-4-20250514", # 2025-05 ]

In token_manager.py:

▼
python
复制代码
"Anthropic": { "claude-haiku-4-5": ModelPricing(0.001, 0.005, 200000, 65536), "claude-sonnet-4-5": ModelPricing(0.003, 0.015, 200000, 65536), "claude-opus-4.1": ModelPricing(0.015, 0.075, 200000, 32768), "claude-sonnet-4": ModelPricing(0.003, 0.015, 200000, 8192), }

Gemini Models (as of Nov 2025)

In capabilities.py:

▼
python
复制代码
models=[ "gemini-3-pro-preview", # 2025-11 "gemini-2.5-flash", # 2025-06 "gemini-2.5-pro", # 2025-06 ]

In token_manager.py (missing gemini-2.5 and gemini-3):

▼
python
复制代码
"Google": { "gemini-1.5-pro": ModelPricing(0.00125, 0.005, 2097152, 8192), "gemini-1.5-flash": ModelPricing(0.000075, 0.0003, 1048576, 8192), # Missing: gemini-2.5-pro, gemini-2.5-flash, gemini-3-pro-preview }

Grok Models (as of Nov 2025)

In capabilities.py:

▼
python
复制代码
models=[ "grok-4-1-fast-reasoning", # 2025-11 "grok-4-1-fast-non-reasoning", # 2025-11 "grok-code-fast-1", # 2025-08 "grok-4", # 2025-07 "grok-4-fast", # 2025-09 "grok-3", # 2025-02 "grok-3-mini", # 2025-05 ]

In token_manager.py (missing grok-3, grok-4 families):

▼
python
复制代码
"xAI": { "grok-2-latest": ModelPricing(0.005, 0.015, 131072, 131072), "grok-2": ModelPricing(0.005, 0.015, 131072, 131072), "grok-2-mini": ModelPricing(0.001, 0.003, 131072, 65536), # Missing: grok-3, grok-4, grok-4-1 families }

Model Name Matching

Important: The names in PROVIDER_PRICING use simplified patterns:

  • "gpt-5" matches gpt-5, gpt-5-preview, gpt-5-*
  • "claude-sonnet-4-5" matches claude-sonnet-4-5-* (any date suffix)
  • "gemini-2.5-pro" is exact match

The token manager uses prefix matching for flexibility.

Common Tasks

Task: Add brand new GPT-5.2 model

  1. Research: Release date, pricing, context window, capabilities
  2. Add to capabilities.py models list and release_dates
  3. Add to token_manager.py PROVIDER_PRICING["OpenAI"]
  4. Run tests
  5. Regenerate docs

Task: Update pricing for existing model

  1. Verify new pricing from official source
  2. Update only token_manager.py PROVIDER_PRICING
  3. No need to touch capabilities.py
  4. Document change in notes if significant

Task: Add new capability to model

  1. Update supported_capabilities in capabilities.py
  2. Add to notes explaining when/how capability works
  3. Update backend implementation if needed
  4. Run tests

Validation Commands

▼
bash
复制代码
# Test capabilities registry uv run pytest massgen/tests/test_backend_capabilities.py -v # Test token manager uv run pytest massgen/tests/test_token_manager.py -v # Generate config with new model massgen --generate-config ./test.yaml --config-backend openai --config-model new-model # Build docs to verify tables cd docs && make html

Programmatic Model Updates

LiteLLM Pricing Database (RECOMMENDED)

The easiest way to get comprehensive model pricing and context window data:

URL: https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json

Coverage: 500+ models across 30+ providers including:

  • OpenAI, Anthropic, Google, xAI
  • Together AI, Groq, Cerebras, Fireworks
  • AWS Bedrock, Azure, Cohere, and more

Data Available:

▼
json
复制代码
{ "gpt-4o": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "supports_vision": true, "supports_function_calling": true, "supports_prompt_caching": true } }

Usage:

▼
python
复制代码
import requests # Fetch latest pricing url = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json" pricing_db = requests.get(url).json() # Get info for a model model_info = pricing_db.get("gpt-4o") input_per_1k = model_info["input_cost_per_token"] * 1000 output_per_1k = model_info["output_cost_per_token"] * 1000

Update token_manager.py from LiteLLM:

  • Convert per-token costs to per-1K costs
  • Extract context window and max output tokens
  • Keep models in reverse chronological order

OpenRouter API (Real-Time)

For the most up-to-date model list with live pricing:

Endpoint: https://openrouter.ai/api/v1/models

Data Available:

  • Real-time pricing (prompt, completion, reasoning, caching)
  • Context windows and max completion tokens
  • Model capabilities and modalities
  • 200+ models from multiple providers

Usage:

▼
python
复制代码
import requests import os headers = {"Authorization": f"Bearer {os.environ['OPENROUTER_API_KEY']}"} response = requests.get("https://openrouter.ai/api/v1/models", headers=headers) models = response.json()["data"] for model in models: print(f"{model['id']}: ${model['pricing']['prompt']} input, ${model['pricing']['completion']} output")

Provider-Specific APIs

ProviderModels APIPricing in API?Recommendation
OpenAIhttps://api.openai.com/v1/models❌ NoUse LiteLLM
ClaudeNo public API❌ NoUse LiteLLM
Geminihttps://generativelanguage.googleapis.com/v1beta/models❌ NoAPI + LiteLLM
Grok (xAI)https://api.x.ai/v1/models❌ NoUse LiteLLM
Together AIhttps://api.together.xyz/v1/models✅ YesAPI directly
Groqhttps://api.groq.com/openai/v1/models❌ NoUse LiteLLM
Cerebrashttps://api.cerebras.ai/v1/models❌ NoUse LiteLLM
Fireworkshttps://api.fireworks.ai/v1/accounts/{id}/models❌ NoUse LiteLLM
Azure OpenAIAzure Management API❌ ComplexManual
Claude CodeNo API❌ NoManual

Automation Script

Create scripts/update_model_pricing.py to automate updates:

▼
python
复制代码
#!/usr/bin/env python3 """Update token_manager.py pricing from LiteLLM database.""" import requests # Fetch LiteLLM database url = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json" pricing_db = requests.get(url).json() # Filter by provider openai_models = {k: v for k, v in pricing_db.items() if v.get("litellm_provider") == "openai"} anthropic_models = {k: v for k, v in pricing_db.items() if v.get("litellm_provider") == "anthropic"} # Generate ModelPricing entries for model_name, info in openai_models.items(): input_per_1k = info["input_cost_per_token"] * 1000 output_per_1k = info["output_cost_per_token"] * 1000 context = info.get("max_input_tokens", 0) max_output = info.get("max_output_tokens", 0) print(f' "{model_name}": ModelPricing({input_per_1k}, {output_per_1k}, {context}, {max_output}),')

Run weekly to keep pricing current:

▼
bash
复制代码
uv run python scripts/update_model_pricing.py

Reference Files

  • Capabilities registry: massgen/backend/capabilities.py
  • Token/pricing manager: massgen/token_manager/token_manager.py
  • Capabilities tests: massgen/tests/test_backend_capabilities.py
  • Config builder: massgen/config_builder.py
  • Doc generator: docs/scripts/generate_backend_tables.py
  • LiteLLM database: https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json
  • OpenRouter API: https://openrouter.ai/docs/overview/models

Important Maintenance Notes

  • Keep models in reverse chronological order - Newest first
  • Use exact API names - Match provider documentation exactly
  • Verify pricing units - Always per 1K tokens in token_manager.py
  • Document uncertainties - If info is estimated/unofficial, note it
  • Update both files - Don't forget token_manager.py when adding models
  • Use LiteLLM for pricing - Comprehensive and frequently updated
  • Test after updates - Run pytest to verify no breaking changes
区块链
商业与营销
软件开发

快捷安装

复制到终端去安装 Skill

npxskillsaddmassgen/MassGen--skill"model-registry-maintainer"
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
🔥热门工具
朱雀AI检测朱雀AI检测
朱雀AI检测助手朱雀AI检测助手
LovartLovart
老鱼简历老鱼简历
WritePass官网WritePass官网
面多多面多多
CursorCursor
星月写作星月写作
朱雀AI检测助手朱雀AI检测助手
零感AI零感AI
Skills 推荐
debug
debug 是一个系统化定位软件缺陷根因的技能,适用于用户报告 'fix'、'broken'、'error' 等问题或测试意外失败时。它通过可验证的假设、最小复现、因果链分析和回归测试,确保在修复前准确定位根本原因。
retrieving-developer-knowledge
retrieving-developer-knowledge 用于搜索、获取和整合 Google 官方开发者文档,覆盖 Google Cloud、AI/Gemini、Android、Chrome、Web、Flutter、Go、Firebase 等平台,适用于查询 gcloud CLI 命令、API 语法、IAM 权限或架构对比等场景。
diff-intake
diff-intake 读取 PR 或分支差异,生成结构化 YAML 变更摘要,用于下游 analytics instrumentation 技能。适用于用户提交 PR 链接、分支对比或原始 diff 后需理解变更内容、评估分析覆盖或启动埋点流程的场景。
definition-of-done-generator
自动生成项目完成标准的规范定义与配置文件,提供符合企业级工作流要求的最佳实践指导,输出可直接投入生产环境的代码和验证结果,适用于需要标准化流程审批、合规审查及跨系统集成的复杂项目管理场景。
implement
实现 Linus Dashboard 的功能开发与集成,基于 TypeScript 和 Python 构建前后端组件,遵循严格的代码规范与架构模式,完成视图、卡片、服务及传感器等模块的创建与验证,确保高质量交付并兼容 Home Assistant 生态。