OpenRouter

Sobre o OpenRouter

O OpenRouter e um agregador de modelos de IA que oferece acesso a 400+ modelos de multiplos provedores com uma unica API key. Sua API e 100% compativel com o formato OpenAI, o que facilita a integracao.

O OpenRouter esta disponivel em todos os planos do QuickClaw. No plano Flex (BYOK), voce usa sua propria chave. Nos planos Starter e Pro, o QuickClaw fornece acesso via chave master da plataforma.

Passo a passo

Formato da chave

A API key do OpenRouter segue este formato:

sk-or-v1-xxxxxxxxxxxxxxxxxxxx

Modelos disponiveis no QuickClaw

Com o OpenRouter no QuickClaw, voce tem acesso a modelos de multiplos provedores (Anthropic, OpenAI, Google, Meta, DeepSeek e mais):

• Anthropic: Claude Opus 4.8 — Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...(1M contexto)
• Anthropic: Claude Opus 4.6 — O mais inteligente da Anthropic. Via OpenRouter.(1M contexto)
• Anthropic: Claude Sonnet 4.6 — Anthropic via OpenRouter — modelo mais recente(1M contexto)
• Anthropic: Claude Sonnet 4.5 — Equilíbrio entre inteligência e velocidade. Via OpenRouter.(1M contexto)
• Anthropic: Claude Haiku 4.5 — Anthropic via OpenRouter — rápido e econômico(200K contexto)
• OpenAI: GPT-5.5(1.1M contexto)
• OpenAI: GPT-5.5 Pro(1.1M contexto)
• OpenAI: GPT-4.1 — Contexto de 1M tokens. Ótimo para documentos longos. Via OpenRouter.(1.0M contexto)
• OpenAI: GPT-5.4 — Modelo flagship mais recente da OpenAI via OpenRouter(1.1M contexto)
• OpenAI: GPT-5.4 Mini — Versão compacta do GPT-5.4 via OpenRouter(400K contexto)
• OpenAI: GPT-5.2 — OpenAI frontier — mais capaz da família GPT-5(400K contexto)
• OpenAI: GPT-5.1 — OpenAI via OpenRouter — upgrade do GPT-5(400K contexto)
• OpenAI: GPT-5 — GPT-5 via OpenRouter(400K contexto)
• OpenAI: GPT-5 Mini — GPT-5 Mini via OpenRouter(400K contexto)
• OpenAI: GPT-5 Nano — OpenAI via OpenRouter — ultra-rápido e barato(400K contexto)
• OpenAI: GPT-4o — Multimodal (texto+visão+áudio). Via OpenRouter.(128K contexto)
• OpenAI: o4 Mini — OpenAI reasoning compacto via OpenRouter(200K contexto)
• OpenAI: GPT-4o-mini — OpenAI via OpenRouter — compacto e eficiente(128K contexto)
• Google: Gemini 3.1 Pro Preview — Google via OpenRouter — modelo mais recente(1.0M contexto)
• Google: Gemma 4 31B (free) — Google Gemma 4 31B Instruct — modelo gratuito de propósito geral, 262K contexto(262K contexto)
• Google: Gemini 2.5 Pro — Modelo avançado do Google. Via OpenRouter.(1.0M contexto)
• Google: Gemma 4 26B A4B (free) — Google Gemma 4 26B A4B Instruct — modelo gratuito menor, 262K contexto(262K contexto)
• Google: Gemini 3 Flash Preview — Google via OpenRouter — Gemini 3 Flash(1.0M contexto)
• Google: Gemini 2.5 Flash — Rápido e econômico do Google. Via OpenRouter.(1.0M contexto)
• OpenAI: GPT-5.4 Nano — OpenAI GPT-5.4 Nano — versão ultra-leve da família 5.4, 400K contexto(400K contexto)
• OpenAI: GPT-5.4 Pro — OpenAI GPT-5.4 Pro — versão top da família 5.4, 1.05M contexto(1.1M contexto)
• Google: Gemini 2.5 Flash Lite — Google via OpenRouter — ultra-baixo custo(1.0M contexto)
• OpenAI: GPT-5.3-Codex — OpenAI GPT-5.3 Codex — especializado em código, 400K contexto(400K contexto)
• OpenAI: GPT-5.2-Codex — OpenAI GPT-5.2 Codex — código, geração anterior, 400K contexto(400K contexto)
• OpenAI: GPT-5.2 Pro — OpenAI GPT-5.2 Pro — versão top da família 5.2, 400K contexto(400K contexto)
• OpenAI: GPT-5.2 Chat — OpenAI GPT-5.2 Chat — conversacional, 128K contexto(128K contexto)
• SpaceXAI: Grok 4.20 — xAI Grok 4.20 — geração mais recente, 2M contexto, raciocínio avançado(2M contexto)
• Meta: Llama 4 Maverick — Open source da Meta. Excelente custo-benefício. Via OpenRouter.(1.0M contexto)
• SpaceXAI: Grok 4.20 Multi-Agent — xAI Grok 4.20 Multi-Agent — orquestração de agentes, 2M contexto(2M contexto)
• Z.ai: GLM 5.1 — Z.ai GLM 5.1 — geração mais recente, 202K contexto, custo baixo(200K contexto)
• Google: Gemini 3.1 Flash Lite Preview — Google Gemini 3.1 Flash Lite Preview — versão paga (substitui o gemini-3-flash-lite-preview que era gratuito), 1M contexto(1.0M contexto)
• Mistral: Mistral Small 4 — Mistral Small 4 (2603) — modelo compacto top da Mistral, 262K contexto(262K contexto)
• Mistral: Devstral 2 2512 — Mistral Devstral 2 (2512) — especializado em código/dev, 262K contexto(262K contexto)
• Qwen: Qwen3.5-Flash — Qwen 3.5 Flash — variante rápida, 1M contexto, custo extremamente baixo(1M contexto)
• Qwen: Qwen3 Max Thinking — Qwen 3 Max com modo thinking — raciocínio extendido, 262K contexto(262K contexto)
• Qwen: Qwen3 Coder Next — Qwen 3 Coder Next — especializado em código, 262K contexto(262K contexto)
• Qwen: Qwen3.5-122B-A10B — Qwen 3.5 122B A10B — modelo grande, 262K contexto(262K contexto)
• ByteDance Seed: Seed 1.6 — ByteDance Seed 1.6 — modelo de propósito geral, 262K contexto(262K contexto)
• DeepSeek: R1 — Reasoning avançado. Muito econômico. Via OpenRouter.(64K contexto)
• DeepSeek: DeepSeek V3.2 — Open-source chinês, ultra-barato — coding e raciocínio(164K contexto)
• MoonshotAI: Kimi K2.5 — Multimodal nativo com visual coding e agent swarm. Via OpenRouter.(262K contexto)
• MiniMax: MiniMax M2.5 — Produtividade real: coding, Word, Excel, PowerPoint. Via OpenRouter.(200K contexto)
• Qwen: Qwen3.5 Plus 2026-02-15 — Alibaba — MoE, visão nativa, contexto 1M(1M contexto)
• Qwen: Qwen3.7 Plus — Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...(1M contexto)
• OpenAI: GPT Chat Latest — GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...(400K contexto)
• NVIDIA: Nemotron 3 Ultra (free) — NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...(1M contexto)
• MoonshotAI: Kimi K2.7 Code — MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...(262K contexto)
• Mistral: Mistral Medium 3.5 — Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...(262K contexto)
• MiniMax: MiniMax M3 — MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...(524K contexto)
• NVIDIA: Nemotron 3 Ultra — NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...(203K contexto)
• Qwen: Qwen3.7 Max — Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...(1M contexto)
• MiniMax: MiniMax M2.7 — Evolução do M2.5 da MiniMax com melhorias em raciocínio e geração. 204K de contexto.(205K contexto)
• Z.ai: GLM 5 Turbo — Modelo otimizado para velocidade da Z-AI (Zhipu). Forte em chinês e inglês. 202K de contexto.(203K contexto)
• NVIDIA: Nemotron 3 Super (free) — Modelo MoE 120B da NVIDIA (12B ativos). Gratuito, forte em raciocínio e código. 262K de contexto.(262K contexto)
• OpenAI: gpt-oss-120b — Modelo open-weight 117B MoE da OpenAI. 5.1B parâmetros ativos. Quantização MXFP4 nativa. Raciocínio configurável.(131K contexto)
• Z.ai: GLM 5 — Modelo principal da Z-AI (Zhipu). Forte em raciocínio, matemática e chinês/inglês. 80K de contexto.(198K contexto)
• Xiaomi: MiMo-V2.5-Pro — MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....(1.0M contexto)
• Qwen: Qwen3.6 27B — Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...(262K contexto)
• Qwen: Qwen3.5 Plus 2026-04-20 — Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...(1M contexto)
• Qwen: Qwen3.6 Max Preview — Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...(262K contexto)
• Qwen: Qwen3.6 35B A3B — Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...(262K contexto)
• SpaceXAI: Grok 4.3 — Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...(1M contexto)
• OpenAI: GPT-5.6 Luna — GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...(1.1M contexto)
• OpenAI: GPT-5.6 Terra — GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...(1.1M contexto)
• OpenAI: GPT-5.6 Luna Pro — GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode(1.1M contexto)
• OpenAI: GPT-5.6 Terra Pro — GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode(1.1M contexto)
• Google: Gemini 3.1 Flash Lite — Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...(1.0M contexto)
• Z.ai: GLM 5.2 — GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...(1.0M contexto)
• Anthropic: Claude Sonnet 5 — Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...(1M contexto)
• OpenAI: GPT-5.6 Sol — GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...(1.1M contexto)
• Google: Gemini 3.5 Flash — Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...(1.0M contexto)
• Sakana: Fugu Ultra — Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...(1M contexto)
• Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) — Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...(66K contexto)
• Qwen: Qwen3.5-9B — Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...(256K contexto)
• Qwen: Qwen3.5-35B-A3B — The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...(256K contexto)
• Anthropic: Claude Opus 4.7 — Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...(1M contexto)
• Google: Gemini 3.1 Pro Preview Custom Tools — Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...(1.0M contexto)
• Qwen: Qwen3.5 397B A17B — The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...(262K contexto)
• Qwen: Qwen3.5-27B — The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...(262K contexto)
• Google: Gemma 4 31B — Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...(262K contexto)
• MoonshotAI: Kimi K2.6 — Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...(262K contexto)
• Xiaomi: MiMo-V2.5 — MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...(1.0M contexto)
• DeepSeek: DeepSeek V4 Flash 0423 — DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...(1.0M contexto)
• OpenAI: GPT-5.6 Sol Pro — GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode(1.1M contexto)
• SpaceXAI: Grok 4.5 — Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.(500K contexto)
• Anthropic: Claude Fable 5 — Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...(1M contexto)
• Z.ai: GLM 5V Turbo — GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...(203K contexto)
• Google: Gemma 4 26B A4B — Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...(262K contexto)
• DeepSeek: DeepSeek V4 Pro 0423 — DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...(1.0M contexto)
• OpenAI: GPT-5.4 Image 2 — [GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...(272K contexto)

Por que OpenRouter?

Disponibilidade