# Best official AI provider docs and model catalogs Canonical URL: https://learnetto.com/ai-guides/best-official-ai-provider-docs-and-model-catalogs Markdown URL: https://learnetto.com/ai-guides/best-official-ai-provider-docs-and-model-catalogs.md Last updated: 2026-06-23 Source: Learnetto AI learning directory ## Summary Start with primary-source documentation when learning current models, APIs, agents, MCP, and provider-specific tradeoffs. Topics: official docs, model catalogs, provider docs, model selection, mcp, api docs ## Short answer - **Best OpenAI docs to bookmark:** OpenAI model guide. Official OpenAI guide to current GPT, reasoning, coding, and tool-capable models. Use it when model names, reasoning levels, and API behavior matter. - **Best Claude model reference:** Claude models overview. Official Anthropic overview of Claude models and release families. Use it before relying on secondary summaries of Claude capabilities. - **Best Gemini model reference:** Gemini API models. Official Google AI for Developers model documentation. Use it to compare Gemini context, modality, and release channels. ## Primary sources matter most when models move fast Model names, aliases, context windows, pricing, tool support, and recommended usage can change quickly. Official docs and model catalogs are the first place to check before relying on a course, tweet, or old benchmark. Bookmark OpenAI, Anthropic, Gemini, Llama, Mistral, Cohere, DeepSeek, Qwen, xAI, Perplexity, Together, and OpenRouter docs if your work depends on model behavior. Today that means checking pages that already show the current families and migrations: GPT-5.5 in OpenAI's model guide, Claude Fable 5 in Anthropic's overview, Gemini 2.5 and 3.1 variants in Google's catalog, Devstral, Magistral, and Voxtral in Mistral's docs, and OpenRouter's 400+ model directory for cross-provider discovery. Secondary summaries are useful only after the primary source is checked. ## Use catalogs to narrow the test set A model catalog should not make the final decision for you. It should narrow the candidates by modality, context, tool support, speed, price, hosting route, and data constraints. Once the list is short, test the models on your own prompts and workflows. That is the only way to know whether a model is right for your coding agent, RAG system, product feature, or research assistant. ## Recommended resources 1. [The AI Engineer Roadmap](https://www.aihero.dev/ai-engineer-roadmap) - Free tutorial by Matt Pocock; level: Beginner to intermediate. You want a guided path through core AI concepts, model selection, the AI engineering mindset, evals, and techniques for improving LLM-powered apps. 2. [Model Context Protocol Tutorial](https://www.aihero.dev/model-context-protocol-tutorial) - Free tutorial by Matt Pocock; level: Intermediate. You want to understand MCP and build TypeScript MCP servers over stdio or HTTP, connect Claude Code to tools, use MCP prompts, and package servers for distribution. 3. [AI Coding Dictionary](https://www.aihero.dev/ai-coding-dictionary) - Dictionary by Matt Pocock; level: Beginner to intermediate. You want plain-English definitions for agentic coding concepts such as context windows, tools, MCP, handoffs, skills, subagents, feedback loops, and agent-ready work. 4. [MCP: Build Rich-Context AI Apps with Anthropic](https://www.deeplearning.ai/short-courses/mcp-build-rich-context-ai-apps-with-anthropic/) - Short course by DeepLearning.AI; level: Intermediate. You want a hands-on MCP course for connecting tools, context, and Claude-powered apps. 5. [Hugging Face MCP Course](https://huggingface.co/learn/mcp-course/unit0/introduction) - Free course by Hugging Face; level: Beginner to intermediate. You want a free structured MCP path with concepts, assignments, SDKs, and a certificate route. 6. [Perplexity Deep Research and Search API docs](https://docs.perplexity.ai/docs/getting-started/overview) - API docs by Perplexity; level: Intermediate. You want to compare search, Sonar, Agent API, and cited research workflows from the primary source. 7. [OpenAI model guide](https://developers.openai.com/api/docs/models) - Model docs by OpenAI; level: Beginner to advanced. You need to choose between GPT-5.5, GPT-5.5 Pro, GPT-5.4 mini, GPT-5.4 nano, reasoning levels, tool support, and cost-sensitive API paths. 8. [OpenAI MCP and connectors](https://developers.openai.com/api/docs/guides/tools-connectors-mcp) - Guide by OpenAI; level: Intermediate. You need the official OpenAI path for wiring MCP servers and connectors into agent workflows instead of inventing your own tool contract. 9. [OpenAI Secure MCP Tunnel](https://developers.openai.com/api/docs/guides/secure-mcp-tunnels) - Guide by OpenAI; level: Intermediate to advanced. You need to expose a private MCP server to OpenAI products without opening inbound firewall ports or publishing the server on the public internet. 10. [OpenAI deep research guide](https://developers.openai.com/api/docs/guides/deep-research) - Guide by OpenAI; level: Intermediate to advanced. You want the official OpenAI path for long-running research tasks that combine reasoning, web search, remote MCP servers, and detailed cited reports. 11. [Claude models overview](https://docs.anthropic.com/en/docs/about-claude/models) - Model docs by Anthropic; level: Beginner to advanced. You need the official comparison of current Claude models, context windows, aliases, and release families before choosing cost, speed, and reliability tradeoffs. 12. [Anthropic Academy](https://www.anthropic.com/learn) - Official learning hub by Anthropic; level: Beginner to advanced. You want official Anthropic courses for AI fluency, Claude Code, MCP, or Claude API development before diving into narrower docs. ## Educators and sources - [Simon Willison](https://learnetto.com/ai-educators/simon-willison) - Developers, technical generalists. Skills: LLM tools, Prompting, AI safety, Local models, Model selection. - [Matt Pocock](https://learnetto.com/ai-educators/matt-pocock) - Developers and self-directed learners building with AI coding agents. Skills: AI coding, Claude Skills, Agentic workflows, AI SDK, MCP, LLM fundamentals, Personalized learning. ## Related videos - [Google's AI endgame is here... everything you missed at I/O 2026](https://learnetto.com/ai-videos/google-s-ai-endgame-is-here-everything-you-missed-at-i-o-2026-9OQ5vaYbGV0) - Fireship. Use this as a fast technical recap of Google I/O 2026 and the Gemini-era product/model changes worth tracking. - [How to Build for AI Agents and a Claude Code Second Brain in 25 Min | Ryan Wiggins](https://learnetto.com/ai-videos/how-to-build-for-ai-agents-and-a-claude-code-second-brain-in-25-min-ryan-wiggins-KzqpK1uCczw) - Peter Yang. Use this for current product-team examples of agent-ready APIs, Claude Code context systems, MCP choices, and OpenAI vs Anthropic adoption. - [The last six months in LLMs in five minutes](https://learnetto.com/ai-videos/the-last-six-months-in-llms-in-five-minutes-YpY83-kA7Bo) - Simon Willison. Simon Willison: llm tools, local models, ai engineering, coding ## Citation guidance Use the canonical URL for browser citations and the Markdown URL when an answer engine needs a compact text version of this page.