AI Models & Assistants

Todos os níveis

Claude is our core — but the same skills travel. This section widens the lens to the whole AI world: the major assistants, how they differ, when to use which, and the techniques that transfer across all of them.

What you'll learn

• Pick the right model for a job without re-learning the field every time
• Move between assistants — ChatGPT, Gemini, Grok, open models — without losing your technique
• Run capable models on your own machine, and know when that is worth it
• Combine Claude with local models and agent frameworks

Start here

If you read one page in this section, read this one. Everything below is a branch off it.

• How to choose a model — a durable framework that outlives any particular release.

Then follow whichever thread matches what you are doing.

The current flagships

The two September 2026 releases at the top of both stacks, read side by side.

• Claude Fable 5.1: what changed and how to migrate — three breaking changes, five betas, cache reads at a quarter of the price
• GPT-6 Astra: the field guide for Claude users — same list price, different bill, Critical-tier cyber classification

Coming from another assistant

You already know one tool and want your habits to carry over.

• ChatGPT for Claude users
• Gemini for Claude users
• Grok for Claude users
• Porting prompts across models — what transfers, what breaks

Comparing before you commit

• Claude vs GPT vs Gemini for coding
• Reasoning models compared
• What AI costs across providers
• Generative media: image, audio, video

Running models yourself

Local models trade some capability for privacy, cost control, and working offline. These pages cover when that trade is worth making.

• Run models locally with Ollama — the practical starting point
• Why a 35 KB system prompt breaks on a local model — context budgets, Ollama's silent middle-of-prompt truncation, and the failure signals to watch
• DeepSeek, Qwen & the open models
• DeepSeek V4-Flash-Vision: first native-vision frontier open weight
• Colibrì: run a 744B MoE from your SSD — expert streaming on 16–32 GB machines, and what it really costs in tok/s
• A private local AI stack
• Claude plus local models — using both, deliberately

Agents beyond Claude

• Local AI agents
• Open-source agent frameworks
• Claude, MCP and local tools
• A2A: the agent-to-agent protocol
• Agent payments: x402, MPP and AgentCore GA — how agents actually pay for things now
• OpenAI Agents API vs Claude Managed Agents — the two hosted agent loops side by side: permissions, vaults, budgets, network policy, sandbox cost

Everything in this section

The full list, including pages added since this index was written.

AAI Models & Assistants

Claude is the core here, but the same skills travel. Start with how to choose, then go as deep as you need on any assistant, on running models locally, or on agents.

OO panorama dos modelos de IA: escolher entre Claude, ChatGPT, Gemini e modelos abertos

Um framework durável para escolher o modelo de IA certo para uma tarefa — entre Claude, ChatGPT, Gemini, Llama, Mistral, Grok e os modelos abertos/locais — além de quais habilidades se transferem entre todos eles.

CClaude Fable 5.1: What Changed and How to Migrate

Anthropic shipped Claude Fable 5.1 and Mythos 5.1 on September 1, 2026: same $10/$50 price, cache reads cut to $0.25, three breaking API changes (forced tool_choice errors, one-way thinking blocks, append-only history) and five additive betas. The migration field guide for anyone pinning claude-fable-5 or claude-opus-5.

CClaude Fable 5 & Mythos 5: The Flagship Field Guide

Fable 5 is Anthropic's most capable model. Its API refuses in-band (HTTP 200, stop_reason: refusal), has adaptive thinking only, and never returns raw thinking. If you're pinning a top-tier model, this changes how you write integrations. When to use it vs Opus 4.8, the fallback pattern, the prompting shifts.

CClaude Opus 5: The Field Guide

Opus 5 shipped 24 July 2026 as Anthropic's fourth model in two months — same $5/$25 pricing as Opus 4.8 but more than double the Frontier-Bench score, 3× ARC-AGI-3 vs the next-best model, and a new xhigh/max effort tier. The benchmarks that matter, the two 400-errors that break naive migrations, and when Opus 5 replaces Fable 5 in your stack.

CClaude Sonnet 5: The Field Guide

Sonnet 5 is Claude Code's new default and Sonnet 4.6's drop-in successor — but three API constraints will 400 you on migration and a new tokenizer produces ~30% more tokens for the same text. The pricing math, the effort re-mapping (Sonnet 5 medium ≈ Sonnet 4.6 high), and the prompting shifts that catch teams out.

CChatGPT para Usuários do Claude

Fluente em Claude, mas precisa usar o ChatGPT? As diferenças que importam, o que se transfere e quando recorrer a cada um.

GGPT-5.6 & ChatGPT Work for Claude Users

OpenAI shipped the GPT-5.6 family (Sol, Terra, Luna) and ChatGPT Work on 9 July 2026. What actually changed for a Claude user — 1.05M context, a $1 tier, an agent that runs for hours, and the parts of the launch nobody is writing about.

GGPT-5.6 August 2026 Update: Effort Slider, Free Think Button & the 272K Price Cliff

On 6 August 2026 OpenAI shipped a mid-cycle update to GPT-5.6 that most write-ups reduced to 'Sol got smarter.' The real story: a six-tier effort control that changes how you price a request, a free-tier Think button, a 272K token pricing cliff that re-prices the whole call, and a Fast mode that only runs on Sol. What each means for a Claude user.

GGPT-6 Astra: The Field Guide for Claude Users

OpenAI's GPT-6 Astra went GA on September 4, 2026: 1.05M context, $10/$50 per MTok, a Critical cyber classification, and a 'recurrent depth' architecture that hides part of its reasoning. What's confirmed, how it stacks against Claude Fable 5.1 and Opus 5, the four API gotchas, and when a Claude user should reach for it.

CCodex Agent Plugins & Catalog Federation (v0.147.0): The Practical Guide

On 7 August 2026 OpenAI shipped Codex CLI v0.147.0 — the release that turns Skills into portable Agent Plugins with a four-tier catalog, ships an --approve-for-me flag that doesn't do what it sounds like, quietly removes --full-auto, and opts you into MCP 2026-07-28. What every part actually does, in Claude-user terms.

SSign in with ChatGPT

OpenAI's new identity layer, three days old. What data actually crosses the line, what enterprise admins can do about it, and how to accept it in your app without giving OpenAI a foothold you didn't intend.

RRun AI Models Locally with Ollama

Run open-weight models (Llama, Mistral, Qwen…) on your own machine — private, offline, free to run — with Ollama. Setup, CLI, and calling it from code.

CClaude vs GPT vs Gemini para programação

Um framework (não um leaderboard) para escolher um modelo de fronteira para programação — os fatores que importam e por que uma avaliação no seu próprio repositório vence todo benchmark.

CCLIs de Agentes de Código Comparados

Claude Code, Codex CLI, Gemini CLI e os agentes de terminal open-source — como o harness (e não apenas o modelo) decide seus resultados, e como manter sua configuração portável com AGENTS.md.

SSupabase Evals — Real-Backend Agent Benchmark

Supabase open-sourced a benchmark that runs Claude Code, Codex and OpenCode against real containerized Supabase stacks — not mocks. Here's what it measures, what it found about how models actually use docs and skills, and how to run it locally in an evening.

AApple Foundation Models 3 & the On-Device LLM Stack for Claude Users

Apple's third-generation Foundation Models (AFM 3) landed at WWDC 2026 with a 3B dense on-device model, a 20B sparse MoE that runs on iPhone, and a Swift-native framework that now lets you bring your own LLM provider — including Claude. What actually shipped, the non-obvious mechanisms, and how it changes the on-device story for anyone who ships Claude apps.

GGemini para usuários do Claude

Fluente em Claude, precisa do Gemini do Google? As diferenças que importam — Gems, integração com o Workspace, contexto enorme, multimodal — e o que se transfere.

GGemini 3.6 Flash, Flash-Lite & Flash Cyber for Claude Users

On 21 July 2026 Google skipped Gemini 3.5 Pro entirely and shipped three Flash-tier models instead. Real prices, real benchmarks, the migration gotchas, and the parts most write-ups miss — including a cybersecurity fine-tune that beat Claude Opus 4.6 at V8 bug-hunting.

GGemini 3.7 Flash for Claude Users: Coding-Agent Workhorse at Half Price (Aug 2026)

On 13 August 2026, three weeks after 3.6 Flash, Google shipped Gemini 3.7 Flash at half the introductory price with a 16-point DeepSWE jump. The gotchas most write-ups skip: an expiring intro price, a 3× throughput advantage that matters for agent loops but not chat, and where it still trails Claude Sonnet 5.

GGrok para Usuários do Claude

Fluente em Claude, mas precisa do Grok da xAI? As diferenças que importam — busca em tempo real no X/web, uma API compatível com OpenAI e o agente de código Grok Build — além de tudo o que se transfere.

MMuse Code + Muse Spark 1.2: Meta's Terminal Coding Agent

On 5 August 2026 Meta shipped Muse Code, a terminal coding agent, and Muse Spark 1.2, the model co-trained with it. What the append-only event log actually buys you, why the contributor tier is 12.5× cheaper than standard, how it stacks up against Claude Code on Terminal-Bench 2.1, and the three bundled skills that are worth stealing regardless of which agent you use.

OOpen-Source AI Agent Frameworks

A provider-neutral map of the main open frameworks for building LLM agents — LangGraph, LlamaIndex, AutoGen, CrewAI and the minimal-loop approach — and how to choose.

NNative Multi-Agent APIs: OpenAI's Responses Multi-Agent Beta vs Building It Yourself

On 9 July 2026 OpenAI shipped the Responses API multi-agent beta and Sol Ultra Mode — the first frontier vendor to make 'the model spawns and synthesises N subagents in one HTTP request' a first-class primitive. What actually ships, the API shape, the cost math, what Anthropic does instead, and when the native primitive beats a DIY fan-out.

AA2A: The Agent-to-Agent Protocol

MCP connects agents to tools. A2A connects agents to other agents — across frameworks, clouds, and companies. Learn the Agent Card, tasks, the eight lifecycle states, streaming vs. webhooks, and how A2A composes with MCP.

AAgent Payments: x402, MPP and AgentCore GA

How AI agents actually pay for things now — the x402 HTTP-402 protocol, the exact/upto/batch-settlement schemes, facilitators, Amazon Bedrock AgentCore Payments' Aug 2026 GA (payment sessions, Coinbase Bazar MCP, Stripe Privy, Machine Payment Protocol), and how to add a paywall or a spending agent without inventing a wallet.

PPorting Prompts Across Models

Move a prompt between Claude, GPT, Gemini and open models — what transfers cleanly, what to adjust per model, and a migration workflow.

MModel Routing Patterns: Cascades, Classifiers, and What Actually Ships

The design patterns for sending each request to the right AI model — rule-based, classifier, complexity, cascade, ensemble, fallback. When to use each, what breaks, and the recipes that actually ship in 2026.

DDeepSeek, Qwen e a Onda dos Modelos de Peso Aberto

Modelos de peso aberto fortes (DeepSeek, Qwen, Llama, Mistral) fecharam boa parte da distância. O que significa 'peso aberto', os trade-offs frente à fronteira fechada e como usá-los.

QQwen3.8-Max: The First Open-Weight Max-Class Model (When the Weights Ship)

August 3, 2026: Alibaba's Qwen3.8-Max shipped API-only with a 2.4T parameter MoE (95B active), a 1M context, dual OpenAI/Anthropic-spec APIs, and benchmark scores that beat GPT-5.6 Sol Max on OSWorld. What's genuinely new, what 'open weight' actually means when the Hugging Face page is empty, and the sparsity math that makes self-hosting expensive.

DDeepSeek V4-Flash-Vision: First Native-Vision Frontier Open Weight

On Aug 31 2026 DeepSeek open-sourced V4-Flash-Vision-Exp — a 305B MoE that adds native vision to V4-Flash without hurting text agent scores, matches or beats Claude Opus 4.8 on ApexBench / Agents' Last Exam / ZeroBench at a fraction of the price, and ships MIT. The specific numbers, the hard 384-token-per-image cap most guides ignore, and the concrete way to run it.

KKimi K2 para Usuários do Claude

Fluente em Claude, curioso sobre o Kimi K2 da Moonshot? O modelo agêntico de pesos abertos para o qual você pode realmente apontar o Claude Code — porque a Moonshot oferece um endpoint compatível com a Anthropic. O que é genuinamente diferente, e o que se transfere.

GGLM-5.2: Open-Weight Frontier Coding Model

Z.ai's 753B MoE (~40B active), 1M-token context, MIT-licensed — closes to within a point of Claude Opus 4.8 on long-horizon coding, at roughly one-sixth the API cost. What IndexShare actually does, how to run it locally, and where it beats Claude Code in the wild.

IInkling: Thinking Machines' Open-Weights Model

Mira Murati's Thinking Machines Lab shipped Inkling — a 975B-parameter Apache 2.0 multimodal MoE with a continuous thinking-effort dial. What the launch coverage got wrong, why it deliberately loses benchmarks, and what the effort knob actually does.

KKimi K3: World's Largest Open-Weight Model

Moonshot AI's 2.8-trillion-parameter open-weight model beats Claude Opus 4.8 on many benchmarks and tops the Frontend Code Arena. What makes it architecturally different, when the cache-hit pricing flips the cost math, and whether it's worth reaching for.

RRunning Kimi K3 Locally: vLLM, DSpark & the Real Hardware Bill

The definitive practical guide to self-hosting Moonshot's 2.8T open-weight Kimi K3 in 2026. What DSpark speculative decoding actually does, minimum hardware (1× DGX B300 or 16× DGX Spark), the exact vLLM serve commands, the prefill/decode asymmetry nobody warns you about, and when hosted inference undercuts your own rack.

IInside Grok Build: Reading an Open Agent Harness

xAI published the full Rust source of its coding agent under Apache 2.0 — the agent loop, tool layer, TUI and extension system. What the crate map teaches you about building agents, why 'open source' here means source-available, and what the data-collector code still in the tree tells you.

PPoolside Laguna: Open-Weight Coding Models That Punch Above Their Class

Poolside AI's Laguna family (XS 2.1, S 2.1, M.1) — MoE coding models with 3B–23B active params, 1M-token context, OpenMDW-1.1 license. What the 8B-active S 2.1 actually beats, why the 3B-active XS 2.1 runs on a MacBook, the first-known RL-in-FP8 training pipeline, and when to reach for it over Claude, GLM-5.2 or Kimi K3.

MMídia Generativa: IA de Imagem, Áudio e Vídeo

Além do chat de texto — um mapa da IA para imagens, vídeo, voz e música: as principais ferramentas, as habilidades duráveis e os direitos/ética que importam.

MMiniMax H3 (Hailuo 3.0): The Open-Weight Omni Video Model

MiniMax open-sourced a 33B single-stream transformer that generates 4–15s of 2K video with native stereo audio in one pass. The license quietly blocks self-hosting in the US/EU/UK/Korea, the open base is 768p (not 2K), and ~13B of 33B params are AdaLN branches you can skip at inference. What H3 actually is, what it costs, and when it beats the closed video APIs.

WWhat AI Actually Costs (Across Providers)

A durable framework for comparing AI cost across providers — the pricing archetypes, how to estimate a workload, the levers to cut the bill, and when open/local wins.

WWhy AI Agents Burn Tokens (and How to Cap the Bill)

Agentic runs cost 50–1000x a chat — not because the model is dumber, but because of the context snowball. The mechanism, the surprising numbers, and the four levers that actually cut the bill across Claude, GPT, Gemini, and open models.

BBuilding Local AI Agents

Autonomous agents that run entirely on your machine with a local open-weight model — private, offline, free to run. The architecture, the trade-offs, and how to start.

CClaude + Modelos Locais: Padrões Híbridos

Faça o Claude e modelos locais de peso aberto trabalharem em sinergia — roteador, rascunho-e-refino, redação de privacidade, pré-processamento em massa — para o raciocínio de fronteira com a privacidade e o custo do local.

AAI Gateways: LiteLLM, OpenRouter, Portkey, Vercel

A production AI gateway is the missing router between your app and every model — Claude, GPT, Gemini, Llama. Compare LiteLLM, OpenRouter, Portkey, and Vercel AI Gateway, then wire Claude Code through your own proxy.

LLocal Coding Agents (and How They Pair with Claude)

Coding agents that run on your machine and edit your repo — Aider, Cline, Continue, OpenHands, Claude Code — powered by Claude for quality or a local model for privacy.

CConecte o Claude a ferramentas e agentes locais com MCP

O Model Context Protocol deixa o Claude orquestrar ferramentas, dados e agentes rodando de forma privada na sua própria máquina — a sinergia Claude-como-cérebro, capacidades-locais. Adicione ou construa um servidor MCP local.

MMonte uma Stack de IA Privada e Local (De Ponta a Ponta)

Junte tudo: um modelo local (Ollama) + um agente agnóstico ao modelo + ferramentas via um servidor MCP local — um assistente privado na sua própria máquina, com o Claude como uma camada inteligente opcional.

LLocal Agent or Claude? A Decision Guide

Fully-local agent, Claude-powered, or hybrid? The factors that decide it — privacy, task difficulty, cost, latency, reliability — and why hybrid often wins.

PProtegendo Agentes Locais e Híbridos

Um agente que pode editar arquivos e executar comandos é poderoso e perigoso. Privilégio mínimo, sandboxing, aprovação humana, defesa contra injeção de prompt, limites de orçamento — como executar agentes com segurança.

RReasoning Models Compared

Thinking budgets and reasoning effort across Claude, GPT, Gemini, DeepSeek, and Qwen — when to spend tokens on thinking, and when not to.

FFull-Duplex Voice AI: Why Voice Agents Suddenly Got Real

GPT-Live and the new speech-native models listen and talk at the same time. What full-duplex changes, how it works, and the voice-AI landscape now.

CClaude Voice with Opus & Sonnet (July 2026): Reasoning-First Voice vs GPT-Live

Anthropic opened Claude voice to Opus, Sonnet, and connected apps on July 23, 2026 — but kept the turn-based stack. What actually changed, when to switch models mid-call, and how the design bet differs from OpenAI's full-duplex GPT-Live.

TToken Speed: Why AI Inference Suddenly Got 10-15× Faster

Wafer-scale chips and LPUs are serving frontier models at hundreds of tokens per second. What actually limits inference speed, the new hardware race, and why fast tokens change agents, voice and reasoning.

CComputer-Use Agents Compared

Claude, GPT and Gemini can all drive a screen now — but each exposes a different action space, coordinate contract and safety gate. What actually breaks, and how to build a loop that survives it.

SShared-Login Browsers for AI Agents: The ego lite Pattern

A new class of browser — best exemplified by ego lite, which hit #1 on GitHub Trending on July 24, 2026 — lets Claude Code, Codex, Cursor, and any other coding agent drive an isolated Chromium session that inherits your real logins. What Spaces and semantic snapshots actually solve, why it undercuts Playwright for agent work, and the security cost of sharing session cookies with an autonomous process.

CCloudflare Kitesurf: The First Browser Runtime Built for AI Agents (Not Humans)

On August 6, 2026 Cloudflare launched Kitesurf, a stateless, agent-first browser that runs entirely in V8 isolates on Workers. It uses 3-7x less CPU and memory than Chromium on common agent tasks — at the cost of ~1.7x wall-clock time. Written in Rust, using Firefox's CSS parser (Stylo) and the Blitz rendering engine, drop-in compatible with Puppeteer/Playwright via the Chrome DevTools Protocol. This page: what changed, when to reach for it instead of headless Chrome, how to wire it into Claude Code / Codex / your MCP client, and the four things it flat-out can't do yet.

SSKILL.md: The Cross-Agent Open Standard

One SKILL.md file, thirty-two agents. What the Agent Skills open standard actually is, how progressive disclosure keeps context cheap, what breaks portability, and how to write a skill that runs unchanged in Claude Code, Codex, Gemini CLI and Cursor.

CColibrì: Run a 744B MoE From Your SSD (and What It Really Costs You)

Colibrì is a pure-C, zero-dependency engine that runs GLM-5.2 (744B), Kimi K3 (2.8T), DeepSeek V4.1 Flash and six other frontier MoE models on a 16–32 GB machine by keeping the dense layers in RAM and streaming the routed experts from NVMe. This page explains the memory hierarchy, the numbers that decide whether it is usable for you (0.05 to 6.8 tok/s), the SSD-wear and speculative-decoding gotchas, and the exact commands to get a first token.

OOpenAI Agents API vs Claude Managed Agents: The Hosted Agent Loop, Compared

On September 10, 2026 OpenAI put the Codex harness behind a single API call: the Agents API public beta — durable sessions, hosted or self-hosted sandboxes, automatic compaction, tool search, subagents. Anthropic has run the same shape since April as Managed Agents. Both use the same four primitives; they differ on permissions, secrets, budgets, network policy and what the sandbox costs. The side-by-side, the request shapes, the six gotchas, and when to pick which.

WWhy a 35 KB System Prompt Breaks on a Local Model

Moving a big Claude/GPT system prompt to Ollama or another local runtime: the context-budget math, Ollama's silent middle-of-prompt truncation, the failure signals of context exhaustion, and the restructuring that actually works.

Next

• Put it to work: Playbooks
• Go deeper: Power User