AI Vendors
Discover the AI providers and models behind ActionFlows AI nodes. Add a provider key under Organization → Integrations → AI Vendors, then select models in Actionflow Studio or Action Agent Studio.
AI Vendors
AI vendors are the providers behind every AI node: models that generate text, produce images, transcribe audio, and reason over your data. Connect a provider once and its models become available in the organization.
Each provider page lists credentials and models. Add the key at Organization → Integrations → AI Vendors, then select the model on a Generate Text / Generate JSON / Generate File node, or in Action Agent Studio.
Catalog
- Alibaba CloudAlibaba Cloud Model Studio provides access to Qwen and other AI models for text generation, embeddings, and multimodal tasks.
- Amazon BedrockFully managed AWS service providing access to foundation models from leading AI providers including Anthropic, Meta, and Amazon.
- AnthropicProvider of the Claude family of AI models, known for advanced reasoning, analysis, and code generation capabilities.
- Anthropic AWSClaude models on AWS using the Anthropic Messages API with AWS authentication.
- AssemblyAIPowerful speech-to-text and audio intelligence APIs for transcription, summarization, and content moderation.
- Azure Cognitive ServicesAI capabilities including speech, language, vision, and decision-making APIs powered by Microsoft Azure.
- Azure OpenAIEnterprise-grade access to OpenAI models with Microsoft Azure's security, compliance, and regional availability.
- BasetenPlatform for deploying and serving machine learning models with auto-scaling infrastructure and optimized model APIs.
- Black Forest LabsImage generation provider behind FLUX models, focused on high-quality text-to-image and image editing workflows.
- ByteDanceAI model platform offering text and multimodal generation capabilities through ByteDance's model infrastructure.
- CartesiaSpeech generation and transcription APIs, including Sonic voices and Ink speech-to-text.
- CerebrasUltra-fast AI inference powered by the world's largest AI chip, delivering exceptional speed for text generation.
- ChutesDecentralized AI inference platform providing access to various open-source language models.
- Cloudflare AI GatewayCaching, rate limiting, analytics, and logging layer for AI API calls across multiple providers.
- Cloudflare Workers AIRun AI models at the edge on Cloudflare's global network with serverless inference and low latency.
- CohereEnterprise AI models specialized in text generation, embeddings, retrieval-augmented generation, and classification.
- CortecsAI inference platform offering access to a variety of language models through a unified API endpoint.
- DeepgramFast and accurate speech-to-text and text-to-speech APIs powered by advanced deep learning models.
- DeepInfraCost-effective serverless AI inference for popular open-source models with high throughput and low latency.
- DeepSeekAdvanced AI models with strong capabilities in reasoning, coding, mathematics, and general language understanding.
- ElevenLabsAI voice generation and text-to-speech platform with natural-sounding, multilingual voice synthesis.
- FalFast and scalable AI inference for generative models including image, video, and audio generation.
- FastRouterAI model routing service that automatically selects the best model for each request based on performance and cost.
- FireworksHigh-performance AI inference with optimized model serving for open-source and fine-tuned language models.
- FirmwareAI infrastructure provider offering model serving and inference capabilities for large language models.
- Fish AudioSpeech generation and transcription APIs for natural voices and audio conversion.
- FriendliOptimized AI model serving with serverless endpoints for fast and cost-efficient language model inference.
- GitHubAI-powered developer tools and model access through GitHub Models for code and text generation.
- GitLab DuoAI-powered development features integrated into the GitLab DevSecOps platform for code assistance and automation.
- GladiaEnterprise-grade speech-to-text APIs with real-time transcription, translation, and audio intelligence features.
- GMI CloudGPU inference for open-weight language models over an OpenAI-compatible API.
- Google GeminiGoogle's multimodal AI models capable of understanding and generating text, images, audio, video, and code.
- Google Vertex AIComprehensive ML platform providing access to Gemini and other Google AI models with enterprise-grade features.
- GroqFastest AI inference powered by custom LPU hardware, delivering ultra-low latency for text generation tasks.
- HeliconeAI observability platform providing logging, monitoring, caching, and analytics for AI model usage.
- Hugging FaceInference APIs for thousands of open-source models across text generation, image, and audio tasks.
- HumeEmpathic AI models that understand and generate emotional expression in voice and natural language.
- InceptionAI model inference platform with developer-friendly APIs and access to various language models.
- InferenceDecentralized AI inference network providing access to open-source language models at competitive pricing.
- IO.NETDecentralized GPU computing for AI inference, offering language model access through distributed infrastructure.
- Kling AIVideo generation provider specialized in text-to-video and image-to-video models for cinematic content creation.
- LlamaMeta's Llama API providing direct access to the Llama family of open-source models for text generation and reasoning.
- LM StudioDesktop application for running local AI models with an OpenAI-compatible inference API server.
- LucidQueryAI platform providing access to language models for text generation and conversational AI applications.
- LumaAI-powered video and 3D content generation models for creative and professional use cases.
- MiniMaxAdvanced AI models for text generation, vision, and multimodal tasks with strong multilingual support.
- MistralEfficient open-weight language models known for strong performance in reasoning, coding, and multilingual tasks.
- MoarkAI platform offering text generation capabilities through a unified model serving infrastructure.
- ModelScopeAlibaba's open-source model community providing inference APIs for a wide range of AI models.
- Moonshot AIProvider of Kimi language models with strong capabilities in long-context understanding and complex reasoning.
- MorphOptimized AI inference focused on fast and cost-effective language model serving for developers.
- NanoGPTSimple and affordable API for accessing various AI language models for text generation tasks.
- NebiusCloud-based AI inference through the Token Factory platform with access to popular language models.
- Novita AIServerless GPU inference for AI models including image generation, language models, and audio processing.
- NVIDIANVIDIA NIM provides optimized inference microservices for AI models with enterprise-grade performance and scalability.
- Ollama CloudCloud-hosted inference for open-source AI models with a simple, developer-friendly API interface.
- OpenAIProvider of GPT, DALL-E, and Whisper models for text generation, image creation, and speech-to-text.
- OpenCode ZenAI coding platform providing model access optimized for code generation and developer workflows.
- OpenRouterUnified API gateway providing access to hundreds of AI models from multiple providers with automatic routing.
- OVHcloudEuropean-hosted AI model inference endpoints with GDPR compliance and data sovereignty guarantees.
- PerplexityAI models enhanced with real-time web search capabilities for up-to-date, source-cited responses.
- PoeQuora's AI platform providing OpenAI-compatible API access to various language models through a unified interface.
- PrivateMode AIPrivacy-focused AI inference platform ensuring data confidentiality and secure model access.
- ProdiaImage generation API designed for fast and cost-effective diffusion model inference and creative media workflows.
- QuiverAIText to SVG image generation and raster to vector conversion.
- ReplicateCloud-based inference for open-source AI models with simple deployment, versioning, and auto-scaling.
- RequestyIntelligent LLM routing service that optimizes cost and performance across multiple AI providers.
- Rev AIAccurate speech-to-text transcription APIs powered by advanced speech recognition technology.
- SAP AI CoreEnterprise AI platform for deploying and managing AI models within the SAP business technology ecosystem.
- ScalewayEuropean cloud-hosted generative AI APIs with a focus on data sovereignty, compliance, and privacy.
- SiliconFlowHigh-performance AI inference for open-source models with competitive pricing and fast throughput.
- SubmodelLightweight AI inference service offering access to various language models through a simple API.
- SyntheticAI model inference platform with developer-friendly APIs and competitive pricing for text generation.
- Together AIFast and affordable inference for leading open-source models with fine-tuning and custom model training.
- UpstageProvider of Solar language models optimized for enterprise use with strong document understanding capabilities.
- Venice AIPrivacy-preserving AI inference platform with no data logging, offering uncensored model access.
- Vercel AI GatewayUnified interface for accessing multiple AI providers with built-in caching, analytics, and fallback routing.
- VivgridAI model inference service providing access to various language models through an OpenAI-compatible API.
- Voyage AISpecialized embeddings provider delivering high-quality vector representations for search, retrieval, and semantic similarity.
- VultrCloud-hosted AI inference with serverless GPU computing for scalable language model serving.
- Weights & BiasesAI experiment tracking, model monitoring, and inference platform through the Weave integration framework.
- xAIProvider of the Grok family of AI models with real-time knowledge and strong reasoning capabilities.
- XiaomiXiaomi MiMo platform providing AI model access for text generation and multimodal understanding tasks.
- Z.AIAI model platform with a focus on enterprise applications and developer-friendly API integration.
- ZenMuxAI gateway service providing unified access to multiple AI providers with intelligent request routing.
- Zhipu AIProvider of the GLM family of language models with strong capabilities in Chinese and English language tasks.
86 AI tools.