Catalogo de Modelos
Todos os modelos de IA disponiveis no QuickClaw com precos e especificacoes.
Modelos disponiveis
O QuickClaw oferece 143 modelos de 4 provedores diferentes. Os precos abaixo sao em USD por Mtok (milhao de tokens) e representam o custo base do provedor. Os precos reais cobrados em BRL variam com a taxa de cambio USD/BRL configurada na plataforma.
Para cada modelo, existem 4 tipos de preco: input, output, cache write e cache read. Para detalhes sobre cache-aware pricing, veja Cache-Aware Pricing.
Tabela de precos por provedor
Anthropic
| Modelo | Input/Mtok | Output/Mtok | Contexto |
|---|---|---|---|
| Anthropic: Claude Opus 4.8 | $5.00 | $25.00 | 1M |
| Anthropic: Claude Opus 4.7 | $5.00 | $25.00 | 1M |
| Anthropic: Claude Opus 4.6 | $5.00 | $25.00 | 1M |
| Claude Opus 4.5 | $5.00 | $25.00 | 200K |
| Claude Opus 4.1 | $15.00 | $75.00 | 200K |
| Anthropic: Claude Sonnet 4.6 | $3.00 | $15.00 | 1M |
| Claude Sonnet 4.5 | $3.00 | $15.00 | 200K |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K |
| Anthropic: Claude Fable 5 | $10.00 | $50.00 | 1M |
| Anthropic: Claude Sonnet 5 | $2.00 | $10.00 | 1M |
OpenAI
| Modelo | Input/Mtok | Output/Mtok | Contexto |
|---|---|---|---|
| OpenAI: GPT-5.5 | $5.00 | $30.00 | 1.1M |
| OpenAI: GPT-5.5 Pro | $30.00 | $180.00 | 1.1M |
| OpenAI: GPT-5.4 | $2.50 | $15.00 | 1.1M |
| OpenAI: GPT-5.3-Codex | $1.75 | $14.00 | 400K |
| OpenAI: GPT-5.4 Mini | $0.750 | $4.50 | 400K |
| OpenAI: GPT-5.2 | $1.75 | $14.00 | 400K |
| OpenAI: GPT-5.4 Nano | $0.200 | $1.25 | 400K |
| OpenAI: GPT-5.1 | $1.25 | $10.00 | 400K |
| OpenAI: GPT-5 | $1.25 | $10.00 | 400K |
| OpenAI: GPT-5 Mini | $0.250 | $2.00 | 400K |
| OpenAI: GPT-5 Nano | $0.050 | $0.400 | 400K |
| OpenAI: GPT-4.1 | $2.00 | $8.00 | 1.0M |
| OpenAI: GPT-4.1 Mini | $0.400 | $1.60 | 1.0M |
| OpenAI: GPT-4.1 Nano | $0.100 | $0.400 | 1.0M |
| OpenAI: o3 | $2.00 | $8.00 | 200K |
| OpenAI: o4 Mini | $1.10 | $4.40 | 200K |
| OpenAI: o3 Mini | $1.10 | $4.40 | 200K |
| OpenAI: GPT-4o | $2.50 | $10.00 | 128K |
| OpenAI: GPT-4o-mini | $0.150 | $0.600 | 128K |
| OpenAI: GPT-5.6 Luna Pro | $0.100 | $0.600 | 1.1M |
| OpenAI: GPT-5.6 Luna | $0.100 | $0.600 | 1.1M |
| OpenAI: GPT-5.6 Terra Pro | $1.00 | $6.00 | 1.1M |
| OpenAI: GPT-5.6 Terra | $1.00 | $6.00 | 1.1M |
| OpenAI: GPT-5.6 Sol Pro | $5.00 | $30.00 | 1.1M |
| OpenAI: GPT-5.6 Sol | $5.00 | $30.00 | 1.1M |
| Modelo | Input/Mtok | Output/Mtok | Contexto |
|---|---|---|---|
| Google: Gemini 3.5 Flash | $1.50 | $9.00 | 1.0M |
| Google: Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1.0M |
| Google: Gemini 3 Flash Preview | $0.500 | $3.00 | 1.0M |
| Google: Gemini 3.1 Flash Lite | $0.250 | $1.50 | 1.0M |
| Google: Gemini 3.1 Flash Lite Preview | $0.250 | $1.50 | 1.0M |
| Google: Gemini 2.5 Pro | $1.25 | $10.00 | 1.0M |
| Google: Gemini 2.5 Flash | $0.300 | $2.50 | 1.0M |
| Google: Gemini 2.5 Flash Lite | $0.100 | $0.400 | 1.0M |
OpenRouter
| Modelo | Input/Mtok | Output/Mtok | Contexto |
|---|---|---|---|
| Anthropic: Claude Opus 4.8 (Fast) | $10.00 | $50.00 | 1M |
| Anthropic: Claude Opus 4.8 | $5.00 | $25.00 | 1M |
| Anthropic: Claude Opus 4.6 | $5.00 | $25.00 | 1M |
| Anthropic: Claude Sonnet 4.6 | $3.00 | $15.00 | 1M |
| Anthropic: Claude Sonnet 4.5 | $3.00 | $15.00 | 1M |
| Anthropic: Claude Haiku 4.5 | $1.00 | $5.00 | 200K |
| OpenAI: GPT-5.5 | $5.00 | $30.00 | 1.1M |
| OpenAI: GPT-5.5 Pro | $30.00 | $180.00 | 1.1M |
| OpenAI: GPT-4.1 | $2.00 | $8.00 | 1.0M |
| OpenAI: GPT-5.4 | $2.50 | $15.00 | 1.1M |
| OpenAI: GPT-5.2 | $1.75 | $14.00 | 400K |
| OpenAI: GPT-5.4 Mini | $0.750 | $4.50 | 400K |
| OpenAI: GPT-5.1 | $1.25 | $10.00 | 400K |
| OpenAI: GPT-5 | $1.25 | $10.00 | 400K |
| OpenAI: GPT-5 Mini | $0.250 | $2.00 | 400K |
| OpenAI: GPT-5 Nano | $0.050 | $0.400 | 400K |
| OpenAI: GPT-4o | $2.50 | $10.00 | 128K |
| OpenAI: o4 Mini | $1.10 | $4.40 | 200K |
| OpenAI: GPT-4o-mini | $0.150 | $0.600 | 128K |
| Google: Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1.0M |
| Google: Gemma 4 31B (free) | $0.0000 | $0.0000 | 262K |
| Google: Gemini 2.5 Pro | $1.25 | $10.00 | 1.0M |
| Google: Gemma 4 26B A4B (free) | $0.0000 | $0.0000 | 131K |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | $0.0000 | $0.0000 | 256K |
| Google: Gemini 3 Flash Preview | $0.500 | $3.00 | 1.0M |
| Google: Gemini 2.5 Flash | $0.300 | $2.50 | 1.0M |
| OpenAI: GPT-5.4 Nano | $0.200 | $1.25 | 400K |
| OpenAI: GPT-5.4 Pro | $30.00 | $180.00 | 1.1M |
| OpenAI: GPT-5.3 Chat | $1.75 | $14.00 | 128K |
| Google: Gemini 2.5 Flash Lite | $0.100 | $0.400 | 1.0M |
| OpenAI: GPT-5.3-Codex | $1.75 | $14.00 | 400K |
| OpenAI: GPT-5.2-Codex | $1.75 | $14.00 | 400K |
| OpenAI: GPT-5.2 Pro | $21.00 | $168.00 | 400K |
| OpenAI: GPT-5.2 Chat | $1.75 | $14.00 | 128K |
| SpaceXAI: Grok 4.20 | $1.25 | $2.50 | 2M |
| Meta: Llama 4 Maverick | $0.200 | $0.800 | 1.0M |
| SpaceXAI: Grok 4.20 Multi-Agent | $1.25 | $2.50 | 2M |
| Z.ai: GLM 5.1 | $0.952 | $2.99 | 203K |
| Google: Gemini 3.1 Flash Lite Preview | $0.250 | $1.50 | 1.0M |
| Mistral: Mistral Small 4 | $0.150 | $0.600 | 262K |
| Qwen: Qwen3.5-Flash | $0.065 | $0.260 | 1M |
| Qwen: Qwen3 Max Thinking | $0.780 | $3.90 | 262K |
| Qwen: Qwen3 Coder Next | $0.120 | $0.800 | 262K |
| Qwen: Qwen3.5-122B-A10B | $0.290 | $2.40 | 262K |
| DeepSeek: R1 | $0.700 | $2.50 | 64K |
| ByteDance Seed: Seed 1.6 | $0.250 | $2.00 | 262K |
| DeepSeek: DeepSeek V3.2 | $0.269 | $0.400 | 164K |
| MoonshotAI: Kimi K2.5 | $0.570 | $2.85 | 262K |
| MiniMax: MiniMax M2.5 | $0.220 | $0.900 | 197K |
| Mistral: Mistral Large 3 2512 | $0.500 | $1.50 | 262K |
| Qwen: Qwen3.5 Plus 2026-02-15 | $0.260 | $1.56 | 1M |
| NVIDIA: Nemotron 3 Ultra (free) | $0.0000 | $0.0000 | 1M |
| MiniMax: MiniMax M3 | $0.300 | $1.20 | 524K |
| Qwen: Qwen3.7 Plus | $0.320 | $1.28 | 1M |
| NVIDIA: Nemotron 3 Ultra | $0.600 | $3.60 | 512K |
| Qwen: Qwen3.7 Max | $1.48 | $4.42 | 1M |
| Mistral: Mistral Medium 3.5 | $1.50 | $7.50 | 262K |
| OpenAI: GPT Chat Latest | $5.00 | $30.00 | 400K |
| MoonshotAI: Kimi K2.7 Code | $0.700 | $3.50 | 262K |
| MiniMax: MiniMax M2.7 | $0.270 | $1.08 | 205K |
| Z.ai: GLM 5 Turbo | $1.20 | $4.00 | 203K |
| NVIDIA: Nemotron 3 Super (free) | $0.0000 | $0.0000 | 262K |
| OpenAI: gpt-oss-120b | $0.037 | $0.170 | 131K |
| Z.ai: GLM 5 | $0.950 | $2.55 | 205K |
| OpenAI: GPT-5.6 Sol | $5.00 | $30.00 | 1.1M |
| Anthropic: Claude Opus 4.7 | $5.00 | $25.00 | 1M |
| OpenAI: GPT-5.6 Sol Pro | $5.00 | $30.00 | 1.1M |
| Qwen: Qwen3.5-9B | $0.100 | $0.150 | 262K |
| Google: Gemma 4 31B | $0.100 | $0.340 | 262K |
| MoonshotAI: Kimi K2.6 | $0.589 | $2.48 | 262K |
| Qwen: Qwen3.5-35B-A3B | $0.140 | $1.00 | 262K |
| Google: Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | 1.0M |
| Xiaomi: MiMo-V2.5 | $0.140 | $0.280 | 1.0M |
| Qwen: Qwen3.5 397B A17B | $0.390 | $2.34 | 262K |
| Qwen: Qwen3.5-27B | $0.195 | $1.56 | 262K |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.088 | $0.176 | 1.0M |
| Z.ai: GLM 5V Turbo | $1.20 | $4.00 | 203K |
| Google: Gemma 4 26B A4B | $0.070 | $0.340 | 262K |
| DeepSeek: DeepSeek V4 Pro | $0.435 | $0.870 | 1.0M |
| OpenAI: GPT-5.4 Image 2 | $8.00 | $15.00 | 272K |
| SpaceXAI: Grok 4.5 | $2.00 | $6.00 | 500K |
| Anthropic: Claude Fable 5 | $10.00 | $50.00 | 1M |
| Xiaomi: MiMo-V2.5-Pro | $0.435 | $0.870 | 1.0M |
| Qwen: Qwen3.6 27B | $0.600 | $3.60 | 262K |
| Qwen: Qwen3.5 Plus 2026-04-20 | $0.300 | $1.80 | 1M |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.500 | $3.00 | 66K |
| Anthropic: Claude Sonnet 5 | $2.00 | $10.00 | 1M |
| Qwen: Qwen3.6 Max Preview | $1.03 | $6.16 | 262K |
| Qwen: Qwen3.6 35B A3B | $0.140 | $1.00 | 262K |
| SpaceXAI: Grok 4.3 | $1.25 | $2.50 | 1M |
| Anthropic: Claude Opus 4.7 (Fast) | $30.00 | $150.00 | 1M |
| OpenAI: GPT-5.6 Luna | $0.100 | $0.600 | 1.1M |
| OpenAI: GPT-5.6 Terra | $1.00 | $6.00 | 1.1M |
| OpenAI: GPT-5.6 Luna Pro | $0.100 | $0.600 | 1.1M |
| OpenAI: GPT-5.6 Terra Pro | $1.00 | $6.00 | 1.1M |
| Z.ai: GLM 5.2 | $0.545 | $1.71 | 1.0M |
| Google: Gemini 3.1 Flash Lite | $0.250 | $1.50 | 1.0M |
| Google: Gemini 3.5 Flash | $1.50 | $9.00 | 1.0M |
| OpenAI: gpt-oss-20b (free) | $0.0000 | $0.0000 | 131K |
| Sakana: Fugu Ultra | $5.00 | $30.00 | 1M |
Precos atualizados automaticamente
Os precos e modelos exibidos nesta pagina sao consultados diretamente do banco de dados da plataforma. Quando novos modelos sao adicionados ou precos mudam, esta pagina reflete automaticamente.
Context Window
O context window define quanto texto o modelo consegue processar de uma vez — incluindo sua mensagem, o system prompt, o historico da conversa e a resposta gerada. Valores maiores permitem conversas mais longas e contextos mais ricos.
Na pratica, o context window raramente e um limitante — uma conversa tipica consome entre 2K e 10K tokens.
Dica de escolha
Modelos mais baratos (Haiku, Flash, mini) sao otimos para uso intenso e respostas rapidas. Modelos premium (Opus, GPT-5) sao melhores para tarefas complexas que exigem raciocinio profundo, analise de codigo ou criacao de conteudo longo.
