Compare produtos de IA em 459 fluxos de trabalho usando estimativas de tráfego, recursos e alternativas.
“Serverless”·368 resultados
RecomeçarInfraestrutura na nuvem sem servidor para cargas de IA e dados
Infraestrutura na nuvem sem servidor para cargas de IA e dados
RunPod is a cloud platform for AI and machine learning workloads that rents GPU compute by the second. It offers Pods for persistent GPU instances, Serverless endpoints that autoscale inference from zero, and multi-node Clusters, plus a Hub of ready-to-deploy open-source models and templates.
RunPod is a cloud platform for AI and machine learning workloads that rents GPU compute by the second. It offers Pods for persistent GPU instances, Serverless endpoints that autoscale inference from zero, and multi-node Clusters, plus a Hub of ready-to-deploy open-source models and templates.
Uma API para mais de 1.500 modelos de mídia generativa prontos para produção
Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
Execute o ComfyUI nativo na nuvem sem instalação, com GPUs rápidas e APIs serverless em um clique
Execute o ComfyUI nativo na nuvem sem instalação, com GPUs rápidas e APIs serverless em um clique
Backend reativo em TypeScript com banco de dados, funções e gateway de IA
Backend reativo em TypeScript com banco de dados, funções e gateway de IA
Nebius is an AI-focused cloud platform that gives teams non-virtualized NVIDIA GPU clusters, managed MLOps tooling, and a serverless inference layer so they can move from experiment to production on one stack.
Nebius is an AI-focused cloud platform that gives teams non-virtualized NVIDIA GPU clusters, managed MLOps tooling, and a serverless inference layer so they can move from experiment to production on one stack.
Inferência sem servidor e descentralizada para modelos de IA abertos
Runware is an AI inference platform that exposes an enormous model catalog — images, video, audio, LLMs and 3D — through a single API endpoint, alongside serverless GPU compute and reserved capacity running on modular data centers the company designs and operates itself. It is aimed at developers and product teams who want to ship generative features without managing infrastructure.
Runware is an AI inference platform that exposes an enormous model catalog — images, video, audio, LLMs and 3D — through a single API endpoint, alongside serverless GPU compute and reserved capacity running on modular data centers the company designs and operates itself. It is aimed at developers and product teams who want to ship generative features without managing infrastructure.
Crie agentes de IA confiáveis visualmente e publique-os na edge sem servidor
Crie agentes de IA confiáveis visualmente e publique-os na edge sem servidor
APIs de inferência serverless de baixo custo para mais de 200 modelos
APIs de inferência serverless de baixo custo para mais de 200 modelos
GPUs serverless para IA em tempo real com cold starts de poucos segundos
Uma nuvem para mais de 200 APIs de modelos, sandboxes de agentes e computação em GPU
Nuvem nativa de IA para empresas
Descreva o software de que precisa e o Blink constrói e aloja
Descreva o software de que precisa e o Blink constrói e aloja
IA de raciocínio open-weight e hospedada de alta eficiência, movida pelo DeepSeek-V4 e pelo R1 a custos de token ultrabaixos.
IA de raciocínio open-weight e hospedada de alta eficiência, movida pelo DeepSeek-V4 e pelo R1 a custos de token ultrabaixos.
Descreva sua ideia no chat e o Lovable a transforma em um app ou site funcional
Descreva sua ideia no chat e o Lovable a transforma em um app ou site funcional
SvectorDB is a natively serverless vector database designed around AWS. It offers pay-per-request pricing, hybrid key-value filtering, built-in text and image vectorizers, and CloudFormation support, making it cheap and simple to add semantic search or recommendations to an existing cloud stack.
SvectorDB is a natively serverless vector database designed around AWS. It offers pay-per-request pricing, hybrid key-value filtering, built-in text and image vectorizers, and CloudFormation support, making it cheap and simple to add semantic search or recommendations to an existing cloud stack.
Dafthunk is an open-source, MIT-licensed visual workflow automation platform that runs on Cloudflare's serverless stack. You drag AI models, browser automations, data pipelines and third-party APIs onto a React Flow canvas, connect them into workflows, and let Cloudflare Workers, Workflows and Durable Objects execute them at the edge — scaling to zero when idle and up to whatever traffic arrives.
Dafthunk is an open-source, MIT-licensed visual workflow automation platform that runs on Cloudflare's serverless stack. You drag AI models, browser automations, data pipelines and third-party APIs onto a React Flow canvas, connect them into workflows, and let Cloudflare Workers, Workflows and Durable Objects execute them at the edge — scaling to zero when idle and up to whatever traffic arrives.
De um prompt a um app web full-stack funcionando, publicado em segundos
De um prompt a um app web full-stack funcionando, publicado em segundos
Descreva sua ideia e o Replit cria um app funcional em minutos
Vivgrid is a managed platform for building and operating AI agents in production. Its core idea is Managed Skills: serverless LLM function calling that runs your agent tools in the cloud, decoupled from the client so prompts, models, and tools can be updated server-side without shipping a new app release. Around that, Vivgrid bundles observability, debugging, evaluation, safety guardrails, orchestration, and globally distributed inference.
Vivgrid is a managed platform for building and operating AI agents in production. Its core idea is Managed Skills: serverless LLM function calling that runs your agent tools in the cloud, decoupled from the client so prompts, models, and tools can be updated server-side without shipping a new app release. Around that, Vivgrid bundles observability, debugging, evaluation, safety guardrails, orchestration, and globally distributed inference.
Crie e publique apps, sites e agentes de IA a partir de um prompt
Crie e publique apps, sites e agentes de IA a partir de um prompt
Execute e construa com modelos de IA abertos localmente ou na nuvem
Execute e construa com modelos de IA abertos localmente ou na nuvem
