AI Model Providers

Router AI integrates with 13 AI model providers: Anthropic, OpenAI, Google, xAI, AWS Bedrock, Mistral, Groq, DeepSeek, SiliconFlow, MiniMax, Zhipu, Doubao (Volcengine Ark), Aliyun Bailian (Qwen). Every request is routed directly to the provider — no pools, no middlemen. Providers AI Model Providers Router AI routes your requests directly to leading AI model providers — no pools, no middlemen, no substitution. Every request hits the real model at the real provider. Anthropic US 9 models Claude — frontier intelligence for coding, agents, and enterprise Reasoning Coding Vision Tool use View profile → OpenAI US 51 models OpenAI models via Router AI — GPT-5 series, GPT-4o, o-series and dozens more, one API key Reasoning Vision Audio Embeddings View profile → Google US 17 models Gemini — multimodal intelligence at 1M+ token context Multimodal Long context Vision Audio View profile → xAI US 6 models xAI Grok OpenAI-Compatible API — Real-Time Reasoning & X Platform Integration Reasoning Vision Fast inference Tool use View profile → AWS Bedrock US (us-east-2) 6 models Nova & Titan — enterprise AI with AWS compliance guarantees Multimodal Long context Embeddings Enterprise View profile → Mistral EU (France) 11 models European AI excellence — from 3B edge models to 675B frontier reasoning Reasoning Coding Vision Multilingual View profile → Groq US 4 models LPU-powered inference — custom hardware built for very low latency Ultra-fast inference Open source models Tool use Low latency View profile → DeepSeek China / Global 4 models Open-source frontier models with 1M context and industry-leading coding performance Reasoning Coding Long context Open source View profile → SiliconFlow Global 21 models SiliconFlow's catalog of 200+ models — rollout in progress OpenAI-compatible API Reasoning Coding Vision View profile → MiniMax Global 7 models M2.7 interleaved thinking & agent-native coding — 204K context, OpenAI-compatible API Reasoning Coding Tool use Agents View profile → Zhipu China 29 models GLM series — China-direct supply with vision, OCR, image, video, and embeddings Vision OCR Reasoning Image generation View profile → Doubao (Volcengine Ark) China 17 models Doubao series — ByteDance's full-stack model platform (chat, vision, reasoning, embedding, image, video) Reasoning Vision Embeddings Image generation View profile → Aliyun Bailian (Qwen) China + Singapore 12 models Aliyun Bailian API — DashScope-Compatible Qwen & Wan Routing, CN + Singapore Failover Reasoning Coding Vision Long context View profile →