Início Modelos Tags Gerar Docs Entrar

Modelos de IA

2 modelos ativos de 5 provedores alimentam as avaliações do Rexiew.

0

Gratuito

1

Plus

1

Pro

5

Provedores

Gratuito Modelos

Gemini 2.5 Flash Lite

Gemini 2.5 Flash Lite by Google is the quickest and cheapest model.

Gemini 2.5 Flash

Gemini 2.5 Flash by Google is a super-quick AI model that spits out answers in seconds.

Quick and modern LLM.

Cheapest GPT-5.4-class model for simple high-volume tasks.

Plus Modelos

5 credits (~$0.05) por análise

Best intelligence at scale for agentic, coding, and professional workflows.

Gemini 2.5 Pro by Google is a powerful AI model that can handle complex tasks and provide detailed answers.

GPT-4o-mini by OpenAI is a powerful AI model that can handle complex tasks and provide detailed answers.

A model from OpenAI that is versatile.

A smaller version of GPT 5.

DeepSeek-V3.2-Exp

The famous open source model out of China.

Claude 4.5 Haiku

A model from Anthropic that is their most affordable offering.

Grok 4 Fast Non-Reasoning

Quicker model from XAI. Retired by xAI on 2026-05-15 — replaced by Grok 4.3 (model 29).

Grok Code Fast 1

Coding model from XAI. Retired by xAI on 2026-05-15 — replaced by Grok 4.3 (model 29).

Powerful thinking model from OpenAI.

Quick and powerful thinking model from OpenAI.

The latest and greatest model from OpenAI.

DeepSeek-V3.2-Exp (Thinking)

The reasoning model from DeepSeek.

Claude 4.5 Sonnet

The most popular model from Anthropic has a great personality.

Grok 4 Fast Reasoning

Quicker and cheaper thinking model from XAI. Retired by xAI on 2026-05-15 — replaced by Grok 4.3 (model 29).

Gemini 3 Pro Preview

Gemini 3 Pro Preview by Google. Replaced by Gemini 3.1 Pro Preview.

Gemini 3 Flash Preview

Gemini 3 Flash Preview by Google is the quickest and cheapest model for thinking.

Gemini 3.1 Pro Preview

Latest Gemini Pro model from Google with improved reasoning capabilities.

Strongest mini model for coding, computer use, and subagents.

Gemini 3.1 Flash Lite Preview

Frontier-class performance from Google at a fraction of the cost.

The latest and most intelligent model from xAI. Tops leaderboards in agentic tool calling and instruction following. 1M token context.

Alibaba Qwen Turbo — fastest and cheapest in the Qwen line. Solid for quick chat, classification, and short-form content. 1M token context.

Alibaba Qwen Plus — best balance of cost, quality, and speed. Strong reasoning and multilingual coverage. 131K token context.

Alibaba Qwen Max — flagship reasoning model. Top performance for complex tasks, deep analysis, and structured output. 32K token context.

Qwen3 Coder Plus

Alibaba Qwen3 Coder Plus — coding-specialized variant. Strong at code generation, refactoring, and tool-use. 1M token context.

Alibaba Qwen VL Max — multimodal flagship. Accepts images alongside text, returns text. Use it for visual Q&A, OCR, and image-grounded reasoning.

DeepSeek V4 Flash

DeepSeek V4 Flash — fast, cheap, with built-in thinking mode. 1M-token context, up to 384K output. Drop-in successor to deepseek-chat / deepseek-reasoner.

DeepSeek V4 Pro

DeepSeek V4 Pro — flagship reasoning model with deeper thinking, stronger tool use, and higher quality output. 1M-token context, up to 384K output. Currently 75% off through 2026-05-31.

Gemini 3.5 Flash

Gemini 3.5 Flash — Google's frontier-intelligence model tuned for speed with superior search and grounding. Excellent for agentic loops, long-horizon coding, and rapid iteration. 1M-token context.

Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite — Google's most cost-efficient model, optimized for high-volume agentic tasks, translation, and simple data processing. 1M-token context.

Claude Sonnet 5

Claude Sonnet 5 — Anthropic's balanced workhorse from the Claude 5 family. Used for AI-generated reviews via subscription sub-agents only.

Kimi K3 — Moonshot's flagship, 2.8T-parameter MoE with native visual understanding and a 1M-token context. Priced level with Claude Sonnet 4.5 for materially more context.

Kimi K2.6 — open-weight MoE with 256K context, text and image input. Sits between gpt-5.4-mini and gpt-5-mini on price with far more context.

Kimi K2.7 Code — agentic coding model, 1T-parameter MoE with 256K context. Handles text, image and video input; tuned for long-context programming tasks.

Kimi K2.7 Code HighSpeed

Kimi K2.7 Code HighSpeed — same model as K2.7 Code at roughly 180 tokens/sec output, for exactly 2x the price. Pick this only when latency matters more than cost.

Pro Modelos

Claude Opus 4.6

25 credits (~$0.25) por análise

The most powerful Claude LLM model.

A larger version of GPT 5.

The flagship Grok 4 model from XAI. Retired by xAI on 2026-05-15 — replaced by Grok 4.3 (model 29).

Claude Fable 5 — Anthropic's Mythos-class flagship, the most capable generally available Claude model. Used for AI-generated reviews via subscription sub-agents only.

Claude Opus 5 — Anthropic's flagship for complex agentic coding and long-horizon work. Materially better one-shot code generation than any earlier Claude.