Pular para o conteúdo
CSuite
Recursos · Chat

Um chat que cria coisas.

Não só respostas: materiais. Descreva o que você precisa e o assistente gera imagens, vídeos, narrações, músicas e efeitos sonoros com os modelos que você escolheu, e depois recorta, apara e converte tudo nos pedidos seguintes. Cada resultado vai para a pasta do seu projeto como um arquivo de verdade.

Escolher

Um modelo de chat, uma equipe inteira por trás.

Escolha o modelo que conduz a conversa (um modelo de ponta na nuvem pelo Runware ou pelo OpenRouter, ou um local pelo Ollama), ou deixe no Auto e o CSuite escolhe um compatível com chat; de qualquer forma, é ele que também escreve as respostas. Por trás dele, cada tipo de mídia tem o próprio espaço: seu modelo de imagem, seu modelo de vídeo, suas vozes. O assistente chama o que o pedido precisar.
Gerar

Peça com suas palavras, receba o material.

Descreva a cena no meio da conversa e o assistente a encaminha para o seu modelo de imagem, sem trocar de espaço de trabalho e sem digitar o prompt de novo. O resultado aparece na própria conversa e é salvo na pasta do seu projeto no mesmo instante.A imagem na conversa é uma geração real do Flux 2 Pro no CSuite, sem retoques, a mesma amostra mostrada na página dele no catálogo.
Iterar

Pedidos seguintes que dão sequência de verdade.

“Recorte em 1:1.” “Deixe em preto fosco.” O assistente sabe que você está falando da última imagem da conversa: edições simples vão direto para o mecanismo de edição local, sem passar por um modelo, e as revisões criativas rodam de imagem para imagem sobre o arquivo que ele acabou de criar. São até seis etapas de ferramentas encadeadas por mensagem: gerar, recortar, converter, pronto.
Multimodal

Todas as modalidades na mesma mesa.

Uma única conversa pode conter uma entrega inteira: uma narração do seu modelo de fala, uma trilha de fundo, um efeito sonoro, um clipe de vídeo que anima a imagem de duas mensagens atrás. Fala, música e efeitos sonoros vão cada um para o próprio espaço de modelo, então pedir uma narração nunca aciona o seu modelo de música.
Espaço de trabalho

Traga seu próprio material.

Uma conversa não é só o que o assistente cria. É também o que você entrega a ele, e a facilidade de tentar uma resposta de novo.

Anexe documentosArraste ou cole PDFs, Markdown, HTML ou texto simples e faça perguntas sobre eles. O texto é extraído e inserido no prompt, e continua disponível para os pedidos seguintes mais adiante na conversa.
Anexe imagensArraste, solte ou cole uma ou mais imagens na conversa. Em um modelo com visão, elas vão para o modelo como entrada de imagem de verdade, esteja ele rodando localmente ou na nuvem.
Veja o modelo pensarUm bloco Raciocínio recolhível mostra o raciocínio do modelo enquanto ele é transmitido, e cada chamada de ferramenta aparece listada passo a passo, com uma marca de concluída ou de falha, então um turno longo nunca é só um indicador girando.
Execute um fluxo de trabalhoPeça um dos seus fluxos de trabalho salvos pelo nome e ele é executado em segundo plano, publicando cada resultado salvo de volta na conversa como anexo.
RegenereNão gostou da resposta? Regenere a última resposta e o turno inteiro é executado de novo, reaproveitando as imagens que você tinha anexado.
Conversas que acompanham o ritmoAs respostas na nuvem chegam token a token, a caixa de prompt continua editável enquanto um turno roda, um botão Ir para a mais recente leva você de volta ao fim, e a conversa ganha nome sozinha depois da primeira troca.
Editar e reenviarReescreva sua última mensagem em vez de discutir com uma que foi mal interpretada. Tudo o que vem depois dela é apagado e o turno roda de novo a partir da versão corrigida.
Copie para foraCopie uma única mensagem, ou a conversa inteira em Markdown, pronta para colar em um documento ou em uma issue.
Saiba quanto custou cada respostaPasse o mouse sobre o rodapé de uma resposta para ver o modelo, os tokens e a duração por trás dela. O OpenRouter informa o custo real cobrado de cada rodada; nos outros, as análises mostram uma estimativa com base nas tarifas publicadas.
Catálogo

Modelos e provedores disponíveis.

Modelos com os quais você pode conversar. Como o chat funciona com chamadas de ferramentas, esta lista é mais restrita que o catálogo completo de texto: um modelo precisa de chamada de função nativa e de um host capaz de executá-la, o que significa Runware ou OpenRouter na nuvem com sua própria chave, ou Ollama localmente, de graça e offline. Os modelos de texto que não cumprem algum desses requisitos continuam disponíveis no espaço de trabalho de Texto.

RunwareNuvem · sua chave de API
OpenRouterNuvem · sua chave de API
OllamaLocal · seu hardware
GPT 6 Astra
Nuvem

OpenAI's flagship GPT-6 model for complex reasoning, coding, research, and long-running agent work, with vision and a 1M-token context window.

OpenAI · OpenRouter · Runware
GPT 6 Astra Pro
Nuvem

GPT 6 Astra in OpenAI's pro reasoning mode, which works longer on each answer for the highest quality on hard tasks.

OpenRouter
GPT 6.1 Sol
Nuvem

OpenAI's update to GPT 6 Sol, the cost-efficient high-end GPT-6 tier, for agentic coding and document work, with vision and a 1M-token context window.

OpenAI · OpenRouter · Runware
GPT 6.1 Terra
Nuvem

OpenAI's fast, efficient GPT-6.1 tier for visual reasoning, computer use and clear writing, improving on GPT 5.6 Terra with a 1M-token context window.

OpenAI · OpenRouter · Runware
GPT 6.1 Sol Pro
Nuvem

GPT 6.1 Sol in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.

OpenRouter
GPT 6.1 Terra Pro
Nuvem

GPT 6.1 Terra in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.

OpenRouter
GPT 6 Sol
Nuvem

OpenAI's cost-efficient high-end GPT-6 tier for demanding coding and agentic work, with vision and a 1M-token context window.

OpenAI · OpenRouter · Runware
GPT 6 Sol Pro
Nuvem

GPT 6 Sol in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.

OpenRouter
GPT 6 Luna
Nuvem

OpenAI's fast, low-cost GPT-6 tier for high-volume chat, classification, and light agentic work, with vision.

OpenAI · OpenRouter · Runware
GPT 6 Luna Pro
Nuvem

GPT 6 Luna in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.

OpenRouter
GPT 5.4
Nuvem

OpenAI's frontier model with advanced reasoning and broad multimodal capabilities.

OpenAI · OpenRouter · Runware · Replicate
GPT 5.6 Luna
Nuvem

OpenAI's fastest, most affordable GPT-5.6 tier — for high-volume, latency-sensitive, and budget-conscious workloads.

OpenAI · OpenRouter · Runware · Replicate
GPT 5.6 Sol
Nuvem

OpenAI's flagship GPT-5.6 tier — leads the family on every benchmark, for frontier coding, long-horizon agentic work, and research.

OpenAI · OpenRouter · Runware · Replicate
Claude Sonnet 5.5
Nuvem

Anthropic's Sonnet-class model for everyday coding and agentic work, a direct upgrade to Sonnet 5 with vision, tool use and a 1M-token context window.

Anthropic · OpenRouter · Runware
Claude Sonnet 5
Nuvem

Anthropic's most agentic Sonnet — frontier-level coding and tool use at Sonnet speed and price, with vision.

Anthropic · OpenRouter · Replicate
Kimi K3.1 Pro
Nuvem

Moonshot's flagship open-weight multimodal reasoning model, post-trained from Kimi K3 for long-horizon coding and agent work, with a 1M-token context.

OpenRouter · Runware
Kimi K3
Nuvem

Moonshot's 2.8T-parameter open-weight mixture-of-experts reasoning model (104B active) with a 1M-token context, built for long-horizon agent work, coding and research.

OpenRouter · Runware
Kimi K2.6
Nuvem

Moonshot's frontier open-weight model (1T parameters) built for long-horizon agentic coding, with a 262K context and native vision.

OpenRouter · Replicate
Claude Opus 5.5
Nuvem

Anthropic's Opus model for long-running agentic coding and knowledge work, with always-on adaptive thinking, vision, and a 1M-token context window.

Anthropic · OpenRouter · Runware · Replicate
Claude Fable 5.2
Nuvem

Anthropic's Fable model for the most demanding reasoning and long-horizon agentic work, improving on Fable 5.1 in coding, reasoning and vision at a lower price, with always-on adaptive thinking and a 1M-token context window.

Anthropic · OpenRouter · Replicate
Claude Fable 5.1
Nuvem

Anthropic's Fable model for the most demanding reasoning and long-horizon agentic work, with always-on adaptive thinking, vision, and a 1M-token context window.

Anthropic · OpenRouter · Runware
Claude Fable 5
Nuvem

Anthropic's Claude 5-family model for the most demanding reasoning, coding, and agentic work — with vision and a 128K output budget.

Anthropic · OpenRouter · Runware · Replicate
Claude Opus 4.8
Nuvem

Anthropic's most capable model — frontier reasoning, coding, and agentic tool use with vision.

Anthropic · OpenRouter · Runware
Claude Haiku 5.5
Nuvem

Anthropic's fastest model, built for high-volume, latency-sensitive work such as classification, extraction, routing and subagent tasks, with vision, tool use and a 1M-token context window.

Anthropic · OpenRouter · Runware
Claude Haiku 4.5
Nuvem

Anthropic's fast, cost-efficient model with strong reasoning, coding, and tool use at low latency.

Anthropic · OpenRouter · Runware · Replicate
Qwen3.8 Max
Nuvem

Alibaba's flagship Qwen3.8 reasoning model for coding, agentic workflows and document analysis, with image input and a 1M-token context window.

OpenRouter
Qwen3.8 Max Prime
Nuvem

A higher-throughput variant of Alibaba's Qwen3.8 Max, served as a separate tier at a higher price.

OpenRouter
Qwen3.8 Flash
Nuvem

Alibaba's fast, low-cost multimodal Qwen3.8 reasoning model for coding assistance, agentic workflows and visual understanding, with a 1M-token context window.

OpenRouter
Qwen3.8 Omni Flash
Nuvem

Alibaba's omni-modal Qwen3.8 reasoning model built around agentic work, which reads text, images, audio and video.

OpenRouter
Muse Wonder
Nuvem

Meta's frontier reasoning model for complex personal and professional agentic tasks, with image input, tool calling and a 1M-token context window.

OpenRouter
Muse Spark 1.3
Nuvem

Meta's multimodal reasoning model for long-running agentic, multi-agent and coding workflows, with image input and a 1M-token context window.

OpenRouter
Muse Spark Open
Nuvem

Meta's open-weight multimodal reasoning model (816B total, 42B active parameters) built for agentic coding, with image input and a 1M-token context window.

OpenRouter
Muse Ember
Nuvem

Meta's smallest and most efficient Muse model for the work agents repeat all day: tool calls, coding subtasks, routing, extraction and long document parsing, with image, video and audio input and a 1M-token context window.

OpenRouter
Grok 4.7
Nuvem

xAI's flagship Grok model for coding, agentic tasks, and knowledge work, with vision and a 500K-token context window.

xAI · OpenRouter · Runware
Grok 4.3
Nuvem

xAI's frontier Grok model with strong reasoning, coding, and agentic tool use, plus vision and real-time knowledge from X.

xAI · OpenRouter · Runware
Gemini 4 Argon
Nuvem

Google's flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving and autonomous multi-step agents, with a shared 1M-token context.

Google · OpenRouter · Runware
Gemini 3.8 Flash
Nuvem

Google's most capable Flash model, with clear gains over 3.7 Flash in software engineering, agentic tasks, and multi-step reasoning, plus vision and a 1M-token context window.

Google · OpenRouter · Runware
Gemini 3.6 Flash
Nuvem

Google's most efficient multimodal Flash model: an updated reasoning stack with stronger coding and computer-use quality, at the same speed and scale as the rest of the Flash line.

Google · OpenRouter · Runware
Gemini 3.1 Pro
Nuvem

Google's most capable multimodal model with deep reasoning and 1M token context.

Google · OpenRouter · Runware · Replicate
Gemma 4 26B (MoE)
NuvemLocal

Google's 26B mixture-of-experts model with long context and strong multimodal reasoning.

Google · Ollama
Gemma 4 31B
NuvemLocal

Google's flagship 31B dense model with 256K context and top-tier text and image understanding.

Google · Ollama
Mistral Large 4
Nuvem

Mistral's largest open-weight model, a multimodal mixture-of-experts built for reasoning, coding and agent work, with vision, tool calling and a 512K-token context window.

OpenRouter
LFM2.5 24B
NuvemLocal

Liquid AI's mixture-of-experts reasoning model with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools.

OpenRouter · Ollama
Nemotron 3.5 Super VL
NuvemLocal

NVIDIA's open multimodal mixture-of-experts model (120B total, 12B active parameters) for coding, reasoning, tool use and document understanding, with image input and a 1M-token context window.

OpenRouter · Ollama
Beam 1.0
Nuvem

Reflection's open-weight reasoning model for coding and long-horizon agentic work: a sparse mixture of experts with 501B total and 23B active parameters, a 1M-token context and tool calling.

OpenRouter
Inkling
Nuvem

Thinking Machines' open-weight multimodal mixture-of-experts model (975B total, 41B active parameters) for reasoning, coding and agent work, reading text, images and audio.

OpenRouter
Inkling Small
Nuvem

The smaller Inkling (276B total, 12B active parameters), close to the larger model on many benchmarks at lower cost and latency, reading text, images and audio.

OpenRouter
M3.1 Flash
Nuvem

MiniMax's low-cost coding and agent model with a 1M-token context and tunable thinking depth, on Runware and OpenRouter.

OpenRouter · Runware
V4.1 Flash
Nuvem

DeepSeek's fast mixture-of-experts model and the first on its Causal Encoder-Decoder architecture, with image input, a 1M-token context and native tool calling.

DeepSeek · OpenRouter · Runware
V4 Pro
Nuvem

DeepSeek's high-capability V4 model (MIT) with a 1M-token context, dual thinking modes, and stronger agentic performance than V4 Flash.

DeepSeek · OpenRouter · Runware
GLM-5.3 Prime
Nuvem

The high-speed variant of Z.ai's GLM-5.3, with the same capabilities at 1.5 to 2 times the output throughput and a higher price.

OpenRouter
GLM-5.3 Flash
Nuvem

Z.ai's natively multimodal GLM-5.3 tier for efficient coding and long-horizon agent tasks, with image input and tool calling.

OpenRouter · Runware
GLM-5.3
Nuvem

Z.ai's flagship open-weights coding model, with a 1M-token context and stronger long-horizon agentic work than GLM-5.2.

OpenRouter · Runware
GLM-5.2
Nuvem

Z.ai's flagship long-horizon coding model, with a 1M-token context and deep-thinking reasoning for end-to-end engineering work.

OpenRouter · Runware
Seed 2.1 Turbo
Nuvem

ByteDance's fast Seed 2.1 reasoning model with a 256K context and output window, native tool calling and image input.

ByteDance · OpenRouter
Seed 2.0 Lite
Nuvem

Balanced Seed 2.0 reasoning model with tool calling and image input at a lower price than Pro.

ByteDance · OpenRouter
Seed 2.0 Mini
Nuvem

The smallest, cheapest Seed 2.0 model for fast everyday tasks, with tool calling and image input.

ByteDance · OpenRouter
Gemma 4 E2B
Local

Google's efficient 2B multimodal model supporting text, image, and audio input.

Ollama
Gemma 4 E4B
Local

Google's efficient 4B multimodal model — stronger reasoning than E2B with text, image, and audio.

Ollama
Gemma 4 12B
Local

Google's 12B multimodal Gemma 4 model with strong text and image understanding.

Ollama
Mistral Small 3.2 24B
Local

Mistral's 24B instruction-tuned model with vision input, robust function calling, and a 128K context.

Ollama
Ministral 3 14B
Local

Mistral's 14B dense edge model (Apache 2.0) tuned for fast on-device reasoning and tool use.

Ollama
Ministral 3 8B
Local

Mistral's efficient 8B dense edge model (Apache 2.0) for on-device chat, reasoning, and tool use.

Ollama
Ministral 3 3B
Local

Mistral's compact 3B dense edge model (Apache 2.0) for fast on-device text generation and tool use.

Ollama
GPT-OSS 20B
Local

OpenAI's open-weight 20B reasoning model (Apache 2.0) with configurable reasoning effort and native tool calling — runs on 16 GB.

Ollama
Phi-4 Mini 3.8B
Local

Microsoft's compact 3.8B model with a 128K context and native function calling.

Ollama
OLMo 3.1 32B
Local

Ai2's fully open 32B model — open weights, data, and training recipe — with long chain-of-thought reasoning.

Ollama
OLMo 3 7B
Local

Ai2's fully open 7B model with open weights, training data, and recipe.

Ollama
OLMo 3 32B
Local

Ai2's fully open 32B model with open weights, training data, and recipe.

Ollama
Laguna XS 2.1 (Q4)
Local

Poolside's 33B (3B active) MoE model for agentic coding and long-horizon local software work, with native reasoning and tool use.

Ollama
Laguna XS 2.1 (Q8)
Local

Poolside's 33B (3B active) MoE agentic-coding model — Q8 quantization for higher fidelity.

Ollama
Laguna XS 2.1 (BF16)
Local

Poolside's 33B (3B active) MoE agentic-coding model — full-precision BF16 weights.

Ollama
Qwen3 0.6B
Local

Alibaba's ultra-compact 0.6B Qwen3 model — runs in-process via HuggingFace or through Ollama, with tool use.

Ollama · Hugging Face
Llama 3.2 1B
Local

Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.

Ollama · Hugging Face
LFM2 24B
Local

Liquid's 24B foundation model with efficient long-context reasoning.

Ollama
Llama 3.1 8B
Local

Meta's 8B instruction-tuned model with 128K context and strong general reasoning.

Ollama
Llama 3.2 3B
Local

Meta's compact 3B instruction-tuned model — fast on-device text generation.

Ollama · Hugging Face
Granite 4.1 3B
Local

IBM's compact 3B instruction-tuned model with multilingual support, tool use, and structured JSON output.

Ollama
Granite 4.1 8B
Local

IBM's 8B dense decoder-only foundation model for general instruction-following, RAG, and code tasks.

Ollama
Granite 4.1 30B
Local

IBM's flagship 30B dense foundation model — strong reasoning across business, coding, and multilingual tasks.

Ollama
Muse Glimmer
Local

Meta Superintelligence Labs' 30B multimodal model for always-on local agents — tuned for tool use, long tasks, and failure recovery.

Ollama
Nemotron 3.5 Lightning
Local

NVIDIA's 30B mixture-of-experts model with 3B active parameters, built as the execution layer for always-on agents.

Ollama
Nemotron 3.5 Bolt
Local

NVIDIA's compact vision-language model (74B total, 9B active parameters), distilled from Nemotron 3.5 Super and tuned to fit a 24 GB NVIDIA GPU for coding, reasoning and tool use.

Ollama
Nemotron 3.5 Bolt E4B
Local

NVIDIA's small vision-language model (8B parameters, 4B effective), post-trained from Gemma 4 E4B for fast local conversations, image understanding and multi-turn tool use; a bundled draft model speeds up generation.

Ollama
Bonsai 2 9B
Local

Prism ML's 9B vision model trained for ternary weights (-1, 0 or +1), about half the size of a standard 4-bit model at close to full-precision quality, with tool calling, thinking and a 256K context.

Ollama
Bonsai 2 27B
Local

Prism ML's 27B vision model trained for ternary weights (-1, 0 or +1), about half the size of a standard 4-bit model at close to full-precision quality, with tool calling, thinking and a 256K context.

Ollama
Nemotron 3
Local

NVIDIA's multimodal Nemotron mixture-of-experts model unifying text and image understanding for enterprise Q&A, summarization, and document intelligence.

Ollama
Qwen3.8 27B
Local

Alibaba's 27B multimodal Qwen 3.8 model with a 256K context — substantial gains in coding, research, and long-horizon agentic tasks, with native image and video understanding.

Ollama
Qwen3.6 27B
Local

Alibaba's 27B multimodal Qwen 3.6 model with a 256K context and strong vision-language reasoning.

Ollama
Qwen3.6 35B
Local

Alibaba's flagship 35B multimodal Qwen 3.6 model for top-tier vision-language reasoning.

Ollama
Qwen3.5 2B
Local

Alibaba's compact 2B multimodal Qwen model with vision input and a 256K context — fast on-device text+image reasoning.

Ollama
Qwen3.5 4B
Local

Alibaba's efficient 4B multimodal Qwen model with vision input and strong multilingual reasoning.

Ollama
Qwen3.5 9B
Local

Alibaba's 9B multimodal Qwen model balancing vision-language reasoning with on-device performance.

Ollama
LFM2.5 8B
Local

Liquid's efficient 8B Liquid Foundation Model tuned for long-context reasoning on-device.

Ollama
LFM3-Omni 2B
Local

Liquid AI's first omni-modal LFM3 model (2.2B parameters), built for on-device use; the app sends it text and images.

Ollama
North Mini Code 1 (Q4)
Local

Cohere's compact code-specialized model tuned for fast local code generation, completion, and refactoring.

Ollama
Ornith 9B
Local

Deep Reinforce's 9B self-improving agentic-coding model (MIT) with 256K context and native tool use.

Ollama
Ornith 35B
Local

Deep Reinforce's flagship 35B self-improving agentic-coding model (MIT) with 256K context — state-of-the-art open-source coding for its size.

Ollama
Ornith 1.5 9B
Local

Deep Reinforce's 9B self-improving model (MIT) with 256K context, image input, and native tool use, tuned for reasoning, coding, and agentic work.

Ollama
Ornith 1.5 35B
Local

Deep Reinforce's 35B MoE self-improving model (MIT) with 256K context, image input, and native tool use, strong across reasoning, coding, and agentic tasks.

Ollama
Ornith 1.5 122B
Local

Deep Reinforce's 122B MoE self-improving model (MIT) with 256K context, image input, and native tool use, the largest Ornith 1.5 size that runs on a single high-memory machine.

Ollama
Qwen3 4B
Local

Alibaba's compact 4B instruction model with strong reasoning and multilingual capabilities.

Ollama · Hugging Face
Perguntas frequentes

Dúvidas sobre chat respondidas.

Como funciona o chat multimodal no CSuite: modelos compatíveis, ferramentas e edições, arquivos, uso offline e custos.

Pagamento único. Seu para sempre.

Sem assinaturas. Sem cobrança por usuário. Sem renovações. Compre o CSuite uma vez, com as atualizações futuras incluídas.

Pagamento seguro pela Stripe. Já tem uma licença? Baixe o app