RADAR DE MODELOS DE IA

Compare modelos de IA com os mesmos critérios

Todos os modelos atualmente listados pela OpenRouter, com dados consistentes sobre modalidades, contexto, preços, configuração e provedores.

ESCOPO DO CATÁLOGO
TODOS PÚBLICOS
modelos
740
provedores
101
última sincronização
20 de nov. de 2026
740 modelos
z-ai logoz-ai

Z.ai: GLM 4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

Contexto
131K
Entrada
text
Saída
text
Entrada: $0.6Saída: $2.2por milhão de tokens
Ver detalhes do modelo →
z-ai logoz-ai

Z.ai: GLM 4.5 Air

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

Contexto
131K
Entrada
text
Saída
text
Entrada: $0.13Saída: $0.85por milhão de tokens
Ver detalhes do modelo →
qwen logoqwen

Qwen: Qwen3 235B A22B Thinking 2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Contexto
128K
Entrada
text
Saída
text
Entrada: $0.45Saída: $3.5por milhão de tokens
Ver detalhes do modelo →
qwen logoqwen

Qwen: Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

Contexto
262K
Entrada
text
Saída
text
Entrada: $0.3Saída: $1por milhão de tokens
Ver detalhes do modelo →
bytedance logobytedance

ByteDance: UI-TARS 7B

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

Contexto
128K
Entrada
image · text
Saída
text
Entrada: $0.1Saída: $0.2por milhão de tokens
Ver detalhes do modelo →
google logogoogle

Google: Gemini 2.5 Flash Lite

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

Contexto
1.0M
Entrada
text · image · file · audio · video
Saída
text
Entrada: $0.1Saída: $0.4por milhão de tokens
Ver detalhes do modelo →
qwen logoqwen

Qwen: Qwen3 235B A22B Instruct 2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Contexto
262K
Entrada
text
Saída
text
Entrada: $0.14Saída: $0.8por milhão de tokens
Ver detalhes do modelo →
moonshotai logomoonshotai

MoonshotAI: Kimi K2 0711

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Contexto
131K
Entrada
text
Saída
text
Entrada: $0.57Saída: $2.3por milhão de tokens
Ver detalhes do modelo →
cognitivecomputations logocognitivecomputations

Venice: Uncensored

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

Contexto
128K
Entrada
text
Saída
text
Entrada: $0.2Saída: $0.9por milhão de tokens
Ver detalhes do modelo →
morph logomorph

Morph: Morph V3 Large

Morph's high-accuracy apply model for complex code edits. 4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initialcode}</code>...

Contexto
262K
Entrada
text
Saída
text
Entrada: $0.9Saída: $1.9por milhão de tokens
Ver detalhes do modelo →
morph logomorph

Morph: Morph V3 Large (batch)

Morph's high-accuracy apply model for complex code edits. 4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initialcode}</code>...

Contexto
262K
Entrada
text
Saída
text
Entrada: $0.45Saída: $0.95por milhão de tokens
Ver detalhes do modelo →
morph logomorph

Morph: Morph V3 Fast

Morph's fastest apply model for code edits. 10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initialcode}</code> <update>{editsnippet}</update>...

Contexto
262K
Entrada
text
Saída
text
Entrada: $0.8Saída: $1.2por milhão de tokens
Ver detalhes do modelo →
morph logomorph

Morph: Morph V3 Fast (batch)

Morph's fastest apply model for code edits. 10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initialcode}</code> <update>{editsnippet}</update>...

Contexto
82K
Entrada
text
Saída
text
Entrada: $0.4Saída: $0.6por milhão de tokens
Ver detalhes do modelo →
mistralai logomistralai

Mistral: Mistral Small 3.2 24B

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Contexto
256K
Entrada
image · text
Saída
text
Entrada: $0.075Saída: $0.2por milhão de tokens
Ver detalhes do modelo →
google logogoogle

Google: Gemini 2.5 Flash

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Contexto
1.0M
Entrada
file · image · text · audio · video
Saída
text
Entrada: $0.3Saída: $2.5por milhão de tokens
Ver detalhes do modelo →
google logogoogle

Google: Gemini 2.5 Pro

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Contexto
1.0M
Entrada
text · image · file · audio · video
Saída
text
Entrada: $1.25Saída: $10por milhão de tokens
Ver detalhes do modelo →
openai logoopenai

OpenAI: o3 Pro

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

Contexto
200K
Entrada
text · file · image
Saída
text
Entrada: $20Saída: $80por milhão de tokens
Ver detalhes do modelo →
google logogoogle

Google: Gemini 2.5 Pro Preview 06-05

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Contexto
1.0M
Entrada
file · image · text · audio
Saída
text
Entrada: $1.25Saída: $10por milhão de tokens
Ver detalhes do modelo →
deepseek logodeepseek

DeepSeek: R1 0528

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Contexto
164K
Entrada
text
Saída
text
Entrada: $0.571Saída: $2.286por milhão de tokens
Ver detalhes do modelo →
mistralai logomistralai

Mistral: Mistral Medium 3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Contexto
131K
Entrada
text · image · file
Saída
text
Entrada: $0.44Saída: $2.2por milhão de tokens
Ver detalhes do modelo →
meta-llama logometa-llama

Meta: Llama Guard 4 12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Contexto
164K
Entrada
image · text
Saída
text
Entrada: $0.18Saída: $0.18por milhão de tokens
Ver detalhes do modelo →
qwen logoqwen

Qwen: Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Contexto
41K
Entrada
text
Saída
text
Entrada: $0.12Saída: $0.5por milhão de tokens
Ver detalhes do modelo →
qwen logoqwen

Qwen: Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Contexto
41K
Entrada
text
Saída
text
Entrada: $0.12Saída: $0.24por milhão de tokens
Ver detalhes do modelo →
qwen logoqwen

Qwen: Qwen3 32B

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Contexto
131K
Entrada
text
Saída
text
Entrada: $0.08Saída: $0.28por milhão de tokens
Ver detalhes do modelo →